{"models":[{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-fable-5","base_model_name":"claude-fable-5","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}},"context_size":1000000,"release_date":"2026-06-07","prompt_logging":true,"prompt_training":false,"zero_data_retention":false,"stream_cancellation_supported":true},"id":"anthropic/claude-fable-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":802.5982,"average_ttft":3.2639,"average_latency":4.0849,"uptime_percent":99.6129,"cache_hit_percentage":0},"throughput":{"average_tps":802.5982,"average_ttft":3.2639,"average_latency":4.0849,"number_of_requests":null},"benchmark":{"cost":13.414521495535714,"intelligence":0.6991150442477876,"latency":1411.5830643938054,"speed":56.92344459267722,"context":141254.5,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-fable-5-1","base_model_name":"claude-fable-5-1","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0.25,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-08-28"},"id":"anthropic/claude-fable-5-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3205.4094,"average_ttft":3.9631,"average_latency":3.9956,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3205.4094,"average_ttft":3.9631,"average_latency":3.9956,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-haiku-4-5","base_model_name":"claude-haiku-4-5","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-haiku-4-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-10-15","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-haiku-4-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":70.0113,"average_ttft":0.859,"average_latency":3.8109,"uptime_percent":99.982,"cache_hit_percentage":0},"throughput":{"average_tps":70.0113,"average_ttft":0.859,"average_latency":3.8109,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-haiku-4-5-20251001","base_model_name":"claude-haiku-4-5-20251001","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-haiku-4-5-20251001"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-10-15","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-haiku-4-5-20251001","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":108.629,"average_ttft":null,"average_latency":12.548,"uptime_percent":99.9985,"cache_hit_percentage":88.9132},"throughput":{"average_tps":108.629,"average_ttft":null,"average_latency":12.548,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-4-5","base_model_name":"claude-opus-4-5","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-opus-4-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-11-24","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-4-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":318.1974,"average_ttft":1.0853,"average_latency":1.2002,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":318.1974,"average_ttft":1.0853,"average_latency":1.2002,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-4-5-20251101","base_model_name":"claude-opus-4-5-20251101","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-opus-4-5-20251101"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-11-24","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-4-5-20251101","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.0872,"average_ttft":null,"average_latency":1.537,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.0872,"average_ttft":null,"average_latency":1.537,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-4-6","base_model_name":"claude-opus-4-6","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2026-02-04","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-4-6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.8553,"average_ttft":null,"average_latency":3.0678,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.8553,"average_ttft":null,"average_latency":3.0678,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-4-7","base_model_name":"claude-opus-4-7","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2026-04-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-4-7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":59.9556,"average_ttft":1.9138,"average_latency":7.0729,"uptime_percent":100,"cache_hit_percentage":73.9097},"throughput":{"average_tps":59.9556,"average_ttft":1.9138,"average_latency":7.0729,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-4-8","base_model_name":"claude-opus-4-8","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name","max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}},"context_size":1000000,"release_date":"2026-05-28","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-4-8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":58.0945,"average_ttft":1.5761,"average_latency":8.9847,"uptime_percent":99.9623,"cache_hit_percentage":0},"throughput":{"average_tps":58.0945,"average_ttft":1.5761,"average_latency":8.9847,"number_of_requests":null},"benchmark":{"cost":13.222583593240094,"intelligence":0.5897435897435898,"latency":3492.740812641026,"speed":38.660661804609404,"context":225741,"passAt4":0.7927927927927928}},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-5","base_model_name":"claude-opus-5","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7752095907502038,"ci_lo":0.6977633822227692,"model":"claude-opus-5","config":"mini_swe_agent_claude_opus_5_max","n_runs":4,"source":"deep-swe","ci_half":0.03872310426371729,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7364864864864865,"pass_at_4":0.8849557522123894,"pass_rate":0.7364864864864865,"n_attempted":444,"ci_attempted":444,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":11.837583271396396,"n_tasks_in_set":113,"median_cost_usd":10.4281505,"mean_agent_steps":99.0427927927928,"reasoning_effort":"max","mean_cache_tokens":14784785.963963963,"mean_input_tokens":15025834.39864865,"n_tasks_attempted":113,"mean_output_tokens":117565.6936936937,"median_agent_steps":90.5,"n_tasks_passed_any":100,"median_input_tokens":12130307.5,"median_output_tokens":113366.5,"mean_duration_seconds":1911.819866231982,"median_duration_seconds":1801.1237265,"median_peak_context_tokens":215810,"median_output_tokens_to_pass":112874}},"context_size":1000000,"release_date":"2026-07-24","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"anthropic/claude-opus-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1649.4972,"average_ttft":2.8224,"average_latency":7.6012,"uptime_percent":99.3188,"cache_hit_percentage":0},"throughput":{"average_tps":1649.4972,"average_ttft":2.8224,"average_latency":7.6012,"number_of_requests":null},"benchmark":{"cost":11.837583271396396,"intelligence":0.7364864864864865,"latency":1911.819866231982,"speed":61.49412702013851,"context":215810,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-opus-5-5","base_model_name":"anthropic/claude-opus-5-5","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":0.2,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-09-22","is_available_on_credits":true},"id":"anthropic/claude-opus-5-5","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":222.5092,"average_ttft":6.8193,"average_latency":12.1953,"uptime_percent":99.599,"cache_hit_percentage":0},"throughput":{"average_tps":222.5092,"average_ttft":6.8193,"average_latency":12.1953,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-sonnet-4-5","base_model_name":"claude-sonnet-4-5","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-sonnet-4-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"context_size":200000,"release_date":"2025-09-29","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-sonnet-4-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.8971,"average_ttft":null,"average_latency":11.2074,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.8971,"average_ttft":null,"average_latency":11.2074,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-sonnet-4-5-20250929","base_model_name":"claude-sonnet-4-5-20250929","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["claude-sonnet-4-5-20250929"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"context_size":200000,"release_date":"2025-09-29","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-sonnet-4-5-20250929","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":712.4249,"average_ttft":1.1851,"average_latency":14.5401,"uptime_percent":99.9875,"cache_hit_percentage":5.9535},"throughput":{"average_tps":712.4249,"average_ttft":1.1851,"average_latency":14.5401,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-sonnet-4-6","base_model_name":"claude-sonnet-4-6","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}},"context_size":200000,"release_date":"2026-02-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-sonnet-4-6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":43.2071,"average_ttft":3.0158,"average_latency":11.5488,"uptime_percent":99.7663,"cache_hit_percentage":0},"throughput":{"average_tps":43.2071,"average_ttft":3.0158,"average_latency":11.5488,"number_of_requests":null},"benchmark":{"cost":5.5223517987804875,"intelligence":0.29933481152993346,"latency":2815.01307943459,"speed":27.055047521796283,"context":146430,"passAt4":0.5663716814159292}},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-sonnet-5","base_model_name":"claude-sonnet-5","max_context_window":200000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"context_size":200000,"release_date":"2026-06-29","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"anthropic/claude-sonnet-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":151.581,"average_ttft":3.6089,"average_latency":7.8635,"uptime_percent":99.8192,"cache_hit_percentage":0},"throughput":{"average_tps":151.581,"average_ttft":3.6089,"average_latency":7.8635,"number_of_requests":null},"benchmark":{"cost":26.399858950791852,"intelligence":0.5384615384615384,"latency":4803.543157789592,"speed":44.57491954174185,"context":409978.5,"passAt4":0.7876106194690266}},{"project":null,"provider":{"project":null,"provider_name":"Anthropic","provider_id":"anthropic","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.503313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-api-key","is_scheduled":true,"list_endpoint":"https://api.anthropic.com/v1/models"},"kind":"host","id":"anthropic"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"anthropic/claude-sonnet-5-5","base_model_name":"anthropic/claude-sonnet-5-5","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.tool_choice_support","capability.vision","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-09-28","is_available_on_credits":true},"id":"anthropic/claude-sonnet-5-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.1824,"average_ttft":null,"average_latency":1.0112,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.1824,"average_ttft":null,"average_latency":1.0112,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-chat","base_model_name":"azure_deepseek/deepseek-chat","max_context_window":64000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure_deepseek/deepseek-chat"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":64000,"release_date":"2024-12-26","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-chat","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-r1","base_model_name":"azure_deepseek/deepseek-r1","max_context_window":64000,"input_cost":8,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure_deepseek/deepseek-r1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":64000,"release_date":"2025-01-20","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-r1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-reasoner","base_model_name":"azure_deepseek/deepseek-reasoner","max_context_window":64000,"input_cost":8,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure_deepseek/deepseek-reasoner"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":64000,"release_date":"2025-01-20","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-reasoner","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-v3","base_model_name":"azure_deepseek/deepseek-v3","max_context_window":64000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure_deepseek/deepseek-v3"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":64000,"release_date":"2024-12-26","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-v3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-v3.2","base_model_name":"azure_deepseek/deepseek-v3.2","max_context_window":128000,"input_cost":0.58,"output_cost":1.68,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":128000,"release_date":"2025-12-01","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-v3.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-v3.2-speciale","base_model_name":"azure_deepseek/deepseek-v3.2-speciale","max_context_window":128000,"input_cost":0.58,"output_cost":1.68,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"context_size":128000,"release_date":"2025-12-01","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_deepseek/deepseek-v3.2-speciale","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure DeepSeek","provider_id":"azure_deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.700861Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_deepseek/deepseek-v4.1-flash","base_model_name":"azure_deepseek/deepseek-v4.1-flash","max_context_window":1000000,"input_cost":0.375,"output_cost":1.5,"cache_hit_input_cost":0.008,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-09-10"},"id":"azure_deepseek/deepseek-v4.1-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":70.3072,"average_ttft":null,"average_latency":4.1136,"uptime_percent":100,"cache_hit_percentage":4.1411},"throughput":{"average_tps":70.3072,"average_ttft":null,"average_latency":4.1136,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure_openai/gpt-5.4","base_model_name":"azure/gpt-5.4","max_context_window":272000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":272000,"release_date":"2026-03-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure_openai/gpt-5.4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":93.4876},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-35-turbo","base_model_name":"azure/gpt-35-turbo","max_context_window":16384,"input_cost":0.5,"output_cost":0.1,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-35-turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16384,"release_date":"2023-03-01","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-35-turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4","base_model_name":"azure/gpt-4","max_context_window":128000,"input_cost":30,"output_cost":60,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2023-03-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4-1106-preview","base_model_name":"azure/gpt-4-1106-preview","max_context_window":128000,"input_cost":10,"output_cost":30,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4-1106-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2023-11-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4-1106-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4-32k","base_model_name":"azure/gpt-4-32k","max_context_window":128000,"input_cost":30,"output_cost":60,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4-32k"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2023-06-13","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4-32k","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4-vision-preview","base_model_name":"azure/gpt-4-vision-preview","max_context_window":128000,"input_cost":10,"output_cost":30,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4-vision-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2023-11-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4-vision-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4.1","base_model_name":"azure/gpt-4.1","max_context_window":1000000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4.1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":123.5802,"average_ttft":4.4441,"average_latency":6.3904,"uptime_percent":100,"cache_hit_percentage":39.8217},"throughput":{"average_tps":123.5802,"average_ttft":4.4441,"average_latency":6.3904,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4.1-mini","base_model_name":"azure/gpt-4.1-mini","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4.1-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4.1-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":49.4303,"average_ttft":1.8454,"average_latency":1.5291,"uptime_percent":99.9984,"cache_hit_percentage":38.3949},"throughput":{"average_tps":49.4303,"average_ttft":1.8454,"average_latency":1.5291,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4.1-nano","base_model_name":"azure/gpt-4.1-nano","max_context_window":1000000,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4.1-nano"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4.1-nano","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":96.9025,"average_ttft":null,"average_latency":2.2534,"uptime_percent":100,"cache_hit_percentage":38.9853},"throughput":{"average_tps":96.9025,"average_ttft":null,"average_latency":2.2534,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4o","base_model_name":"azure/gpt-4o","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4o"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4o","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4o-2024-08-06","base_model_name":"azure/gpt-4o-2024-08-06","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4o-2024-08-06"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4o-2024-08-06","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-4o-mini","base_model_name":"azure/gpt-4o-mini","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-4o-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-18","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-4o-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":1.7705,"average_ttft":null,"average_latency":1.1297,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.7705,"average_ttft":null,"average_latency":1.1297,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5","base_model_name":"azure/gpt-5","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":400000,"release_date":"2025-08-07","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5-codex","base_model_name":"azure/gpt-5-codex","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-09-11","is_available_on_credits":false},"id":"azure/gpt-5-codex","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5-mini","base_model_name":"azure/gpt-5-mini","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-5-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-07","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-5-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":53.9287,"average_ttft":null,"average_latency":2.6308,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":53.9287,"average_ttft":null,"average_latency":2.6308,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5-nano","base_model_name":"azure/gpt-5-nano","max_context_window":400000,"input_cost":0.05,"output_cost":0.4,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-07","is_available_on_credits":false},"id":"azure/gpt-5-nano","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":55.2012,"average_ttft":null,"average_latency":1.3587,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":55.2012,"average_ttft":null,"average_latency":1.3587,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5-pro","base_model_name":"azure/gpt-5-pro","max_context_window":400000,"input_cost":15,"output_cost":120,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-10-06","is_available_on_credits":false},"id":"azure/gpt-5-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.1","base_model_name":"azure/gpt-5.1","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","is_available_on_credits":false},"id":"azure/gpt-5.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.3043,"average_ttft":null,"average_latency":1.4868,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.3043,"average_ttft":null,"average_latency":1.4868,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.1-codex","base_model_name":"azure/gpt-5.1-codex","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","is_available_on_credits":false},"id":"azure/gpt-5.1-codex","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.1-codex-max","base_model_name":"azure/gpt-5.1-codex-max","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-12-04","is_available_on_credits":false},"id":"azure/gpt-5.1-codex-max","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.1-codex-mini","base_model_name":"azure/gpt-5.1-codex-mini","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","is_available_on_credits":false},"id":"azure/gpt-5.1-codex-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.2","base_model_name":"azure/gpt-5.2","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/gpt-5.2"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-11","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-5.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.2-codex","base_model_name":"azure/gpt-5.2-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-01-14","is_available_on_credits":false},"id":"azure/gpt-5.2-codex","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.3-codex","base_model_name":"azure/gpt-5.3-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-02-24","is_available_on_credits":false},"id":"azure/gpt-5.3-codex","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.4","base_model_name":"azure/gpt-5.4","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cost_tiers","display_name","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":272000,"release_date":"2026-03-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/gpt-5.4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":50.9451,"average_ttft":null,"average_latency":2.6542,"uptime_percent":100,"cache_hit_percentage":2.4213},"throughput":{"average_tps":50.9451,"average_ttft":null,"average_latency":2.6542,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.4-mini","base_model_name":"azure/gpt-5.4-mini","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-17","is_available_on_credits":false},"id":"azure/gpt-5.4-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.4-nano","base_model_name":"azure/gpt-5.4-nano","max_context_window":400000,"input_cost":0.2,"output_cost":1.25,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-17","is_available_on_credits":false},"id":"azure/gpt-5.4-nano","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.2361,"average_ttft":null,"average_latency":1.5283,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.2361,"average_ttft":null,"average_latency":1.5283,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.4-pro","base_model_name":"azure/gpt-5.4-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1050000,"release_date":"2026-03-05","is_available_on_credits":false},"id":"azure/gpt-5.4-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.5","base_model_name":"azure/gpt-5.5","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":1050000,"release_date":"2026-04-24","is_available_on_credits":false},"id":"azure/gpt-5.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.6-luna","base_model_name":"azure/gpt-5.6-luna","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}},"context_size":1050000,"release_date":"2026-07-09"},"id":"azure/gpt-5.6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":true,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":56.2925,"average_ttft":1.2396,"average_latency":2.6575,"uptime_percent":99.9998,"cache_hit_percentage":0.0781},"throughput":{"average_tps":56.2925,"average_ttft":1.2396,"average_latency":2.6575,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.6-sol","base_model_name":"azure/gpt-5.6-sol","max_context_window":1050000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.4,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}},"context_size":1050000,"release_date":"2026-07-09"},"id":"azure/gpt-5.6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":true,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":361.181,"average_ttft":3.4046,"average_latency":4.6223,"uptime_percent":99.4493,"cache_hit_percentage":90.3589},"throughput":{"average_tps":361.181,"average_ttft":3.4046,"average_latency":4.6223,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-5.6-terra","base_model_name":"azure/gpt-5.6-terra","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}},"context_size":1050000,"release_date":"2026-07-09"},"id":"azure/gpt-5.6-terra","is_byok":true,"effective_discount_rate":0,"response_api_support":true,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":65.4167,"average_ttft":1.1142,"average_latency":3.9345,"uptime_percent":99.9965,"cache_hit_percentage":65.7008},"throughput":{"average_tps":65.4167,"average_ttft":1.1142,"average_latency":3.9345,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-6-astra","base_model_name":"azure/gpt-6-astra","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7698044042186275,"ci_lo":0.7124964807371247,"model":"gpt-6-astra","config":"mini_swe_agent_gpt_6_astra_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02865396174075141,"harness":"mini-swe-agent","version":"v1.1","n_passed":335,"provider":"openai","ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":335,"pass_at_1":0.7411504424778761,"pass_at_4":0.8053097345132744,"pass_rate":0.7411504424778761,"cost_basis":"Current pricing at all context lengths: $10/M uncached input, $12.50/M cache writes, $1/M cache reads, $50/M output; no separate compute-unit fee.","n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.429117203539823,"n_tasks_in_set":113,"median_cost_usd":3.8406789999999997,"mean_agent_steps":28.754424778761063,"reasoning_effort":"xhigh","mean_cache_tokens":1326921.6836283186,"mean_input_tokens":1456927.0929203539,"n_tasks_attempted":113,"mean_compute_units":752203.0973451327,"mean_output_tokens":29557.327433628318,"median_agent_steps":26,"n_tasks_passed_any":91,"median_input_tokens":1163918.5,"completed_by_attempt":[113,113,113,113],"median_compute_units":662371.5,"median_output_tokens":28542.5,"pass_rate_by_attempt":[0.7079646017699115,0.7345132743362832,0.7787610619469026,0.7433628318584071],"mean_duration_seconds":1132.4004424778761,"mean_reasoning_tokens":11255.66592920354,"mean_cache_read_tokens":1326921.6836283186,"mean_cache_write_tokens":129710.02212389381,"median_duration_seconds":959,"median_reasoning_tokens":10434,"median_cache_read_tokens":1035975,"median_cache_write_tokens":103995,"mean_uncached_input_tokens":295.3871681415929,"median_peak_context_tokens":null,"median_output_tokens_to_pass":28361,"median_uncached_input_tokens":87}},"context_size":1050000,"release_date":"2026-09-03","is_available_on_credits":false},"id":"azure/gpt-6-astra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":4.429117203539823,"intelligence":0.7411504424778761,"latency":1132.4004424778761,"speed":26.101479940216276,"context":null,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-6-luna","base_model_name":"azure/gpt-6-luna","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1050000,"release_date":"2026-09-22","is_available_on_credits":false},"id":"azure/gpt-6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":78.9608,"average_ttft":1.1181,"average_latency":4.6321,"uptime_percent":99.9993,"cache_hit_percentage":28.6655},"throughput":{"average_tps":78.9608,"average_ttft":1.1181,"average_latency":4.6321,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-6-sol","base_model_name":"azure/gpt-6-sol","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1050000,"release_date":"2026-09-22","is_available_on_credits":false},"id":"azure/gpt-6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":36.914,"average_ttft":3.0537,"average_latency":2.6502,"uptime_percent":100,"cache_hit_percentage":23.7501},"throughput":{"average_tps":36.914,"average_ttft":3.0537,"average_latency":2.6502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/gpt-chat-latest","base_model_name":"azure/gpt-chat-latest","max_context_window":400000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-08-06","is_available_on_credits":false},"id":"azure/gpt-chat-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/o1","base_model_name":"azure/o1","max_context_window":200000,"input_cost":15,"output_cost":60,"cache_hit_input_cost":7.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/o1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2024-12-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/o1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/o3","base_model_name":"azure/o3","max_context_window":200000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/o3"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-16","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/o3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/o3-mini","base_model_name":"azure/o3-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.55,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/o3-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-01-31","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/o3-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Azure OpenAI","provider_id":"azure_openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.858844Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"azure_openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"azure/o4-mini","base_model_name":"azure/o4-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["azure/o4-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-16","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"azure/o4-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"","max_context_window":1048576,"input_cost":0.13,"output_cost":0.26,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-06"},"id":"baseten/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":570.7455,"average_ttft":1.8169,"average_latency":3.2523,"uptime_percent":99.7984,"cache_hit_percentage":39.1086},"throughput":{"average_tps":570.7455,"average_ttft":1.8169,"average_latency":3.2523,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.132,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-13"},"id":"baseten/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":36.0591,"average_ttft":null,"average_latency":1.7471,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.0591,"average_ttft":null,"average_latency":1.7471,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.007,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"baseten/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":234.6484,"average_ttft":1.964,"average_latency":2.4041,"uptime_percent":99.9293,"cache_hit_percentage":0.7918},"throughput":{"average_tps":234.6484,"average_ttft":1.964,"average_latency":2.4041,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/moonshotai/Kimi-K3","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-26"},"id":"baseten/moonshotai/Kimi-K3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":39.5906,"average_ttft":null,"average_latency":1.6165,"uptime_percent":100,"cache_hit_percentage":74.4186},"throughput":{"average_tps":39.5906,"average_ttft":null,"average_latency":1.6165,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","base_model_name":"","max_context_window":202800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.12,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-04"},"id":"baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.8317,"average_ttft":null,"average_latency":0.6948,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.8317,"average_ttft":null,"average_latency":0.6948,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"baseten/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":128072,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"baseten/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":95.0077,"average_ttft":0.7319,"average_latency":1.1645,"uptime_percent":100,"cache_hit_percentage":2.7754},"throughput":{"average_tps":95.0077,"average_ttft":0.7319,"average_latency":1.1645,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"baseten/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16"},"id":"baseten/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":122.1934,"average_ttft":2.745,"average_latency":4.4414,"uptime_percent":100,"cache_hit_percentage":87.2235},"throughput":{"average_tps":122.1934,"average_ttft":2.745,"average_latency":4.4414,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/zai-org/GLM-5.2-Fast","base_model_name":"","max_context_window":1048576,"input_cost":2.1,"output_cost":6.6,"cache_hit_input_cost":0.21,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-23"},"id":"baseten/zai-org/GLM-5.2-Fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":77.5439,"average_ttft":null,"average_latency":0.8253,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":77.5439,"average_ttft":null,"average_latency":0.8253,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/zai-org/GLM-5.3","base_model_name":"","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-28"},"id":"baseten/zai-org/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":252.9626,"average_ttft":2.4515,"average_latency":8.4827,"uptime_percent":100,"cache_hit_percentage":96.6054},"throughput":{"average_tps":252.9626,"average_ttft":2.4515,"average_latency":8.4827,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/zai-org/GLM-5.3-Fast","base_model_name":"","max_context_window":1048576,"input_cost":2.1,"output_cost":6.6,"cache_hit_input_cost":0.21,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-01"},"id":"baseten/zai-org/GLM-5.3-Fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":62.5671,"average_ttft":null,"average_latency":1.0229,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":62.5671,"average_ttft":null,"average_latency":1.0229,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Baseten","provider_id":"baseten","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.636948Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.baseten.co/v1/models"},"kind":"host","id":"baseten"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"baseten/zai-org/GLM-5.3-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"baseten/zai-org/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":45.4969,"average_ttft":null,"average_latency":1.4067,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":45.4969,"average_ttft":null,"average_latency":1.4067,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/amazon.nova-lite-v1:0","base_model_name":"bedrock/amazon.nova-lite-v1:0","max_context_window":300000,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/amazon.nova-lite-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/deepseek.v3-v1:0","base_model_name":"bedrock/deepseek.v3-v1:0","max_context_window":163840,"input_cost":0.58,"output_cost":1.68,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/deepseek.v3-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/deepseek.v3.2","base_model_name":"bedrock/deepseek.v3.2","max_context_window":164000,"input_cost":0.62,"output_cost":1.85,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/deepseek.v3.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.amazon.nova-2-lite-v1:0","base_model_name":"bedrock/global.amazon.nova-2-lite-v1:0","max_context_window":1000000,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.amazon.nova-2-lite-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0","base_model_name":"bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-haiku-4-5-20251001-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0","base_model_name":"bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-opus-4-5-20251101-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-opus-5-5","base_model_name":"bedrock/global.anthropic.claude-opus-5-5","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-opus-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-sonnet-4-20250514-v1:0","base_model_name":"bedrock/global.anthropic.claude-sonnet-4-20250514-v1:0","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-sonnet-4-20250514-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0","base_model_name":"bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-sonnet-4-5-20250929-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.anthropic.claude-sonnet-5-5","base_model_name":"bedrock/global.anthropic.claude-sonnet-5-5","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.anthropic.claude-sonnet-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.moonshotai.kimi-k3","base_model_name":"bedrock/global.moonshotai.kimi-k3","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.moonshotai.kimi-k3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-5.6-luna","base_model_name":"bedrock/global.openai.gpt-5.6-luna","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-5.6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-5.6-sol","base_model_name":"bedrock/global.openai.gpt-5.6-sol","max_context_window":1050000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.4,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-5.6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-5.6-terra","base_model_name":"bedrock/global.openai.gpt-5.6-terra","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-5.6-terra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-6-astra","base_model_name":"bedrock/global.openai.gpt-6-astra","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-6-astra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-6-luna","base_model_name":"bedrock/global.openai.gpt-6-luna","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-6-sol","base_model_name":"bedrock/global.openai.gpt-6-sol","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/global.openai.gpt-6.1-sol","base_model_name":"bedrock/global.openai.gpt-6.1-sol","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/global.openai.gpt-6.1-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/google.gemma-3-12b-it","base_model_name":"bedrock/google.gemma-3-12b-it","max_context_window":128000,"input_cost":0.09,"output_cost":0.29,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/google.gemma-3-12b-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/google.gemma-3-4b-it","base_model_name":"bedrock/google.gemma-3-4b-it","max_context_window":128000,"input_cost":0.04,"output_cost":0.08,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/google.gemma-3-4b-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/meta.llama3-1-70b-instruct-v1:0","base_model_name":"bedrock/meta.llama3-1-70b-instruct-v1:0","max_context_window":128000,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/meta.llama3-1-70b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/meta.llama3-1-8b-instruct-v1:0","base_model_name":"bedrock/meta.llama3-1-8b-instruct-v1:0","max_context_window":128000,"input_cost":0.22,"output_cost":0.22,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/meta.llama3-1-8b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/meta.llama3-70b-instruct-v1:0","base_model_name":"bedrock/meta.llama3-70b-instruct-v1:0","max_context_window":8000,"input_cost":2.65,"output_cost":3.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/meta.llama3-70b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/meta.llama3-8b-instruct-v1:0","base_model_name":"bedrock/meta.llama3-8b-instruct-v1:0","max_context_window":8000,"input_cost":0.3,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/meta.llama3-8b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/minimax.minimax-m2","base_model_name":"bedrock/minimax.minimax-m2","max_context_window":1000000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/minimax.minimax-m2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/minimax.minimax-m2.1","base_model_name":"bedrock/minimax.minimax-m2.1","max_context_window":196000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/minimax.minimax-m2.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/minimax.minimax-m2.5","base_model_name":"bedrock/minimax.minimax-m2.5","max_context_window":196000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/minimax.minimax-m2.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.devstral-2-123b","base_model_name":"bedrock/mistral.devstral-2-123b","max_context_window":256000,"input_cost":0.4,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.devstral-2-123b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.magistral-small-2509","base_model_name":"bedrock/mistral.magistral-small-2509","max_context_window":128000,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.magistral-small-2509","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.ministral-3-14b-instruct","base_model_name":"bedrock/mistral.ministral-3-14b-instruct","max_context_window":128000,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.ministral-3-14b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.ministral-3-3b-instruct","base_model_name":"bedrock/mistral.ministral-3-3b-instruct","max_context_window":128000,"input_cost":0.1,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.ministral-3-3b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.ministral-3-8b-instruct","base_model_name":"bedrock/mistral.ministral-3-8b-instruct","max_context_window":128000,"input_cost":0.15,"output_cost":0.15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.ministral-3-8b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.mistral-7b-instruct-v0:2","base_model_name":"bedrock/mistral.mistral-7b-instruct-v0:2","max_context_window":32000,"input_cost":0.15,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.mistral-7b-instruct-v0:2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.mistral-large-2402-v1:0","base_model_name":"bedrock/mistral.mistral-large-2402-v1:0","max_context_window":32000,"input_cost":4,"output_cost":12,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.mistral-large-2402-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.mistral-large-2407-v1:0","base_model_name":"bedrock/mistral.mistral-large-2407-v1:0","max_context_window":null,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.mistral-large-2407-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.mistral-large-3-675b-instruct","base_model_name":"bedrock/mistral.mistral-large-3-675b-instruct","max_context_window":256000,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.mistral-large-3-675b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.mixtral-8x7b-instruct-v0:1","base_model_name":"bedrock/mistral.mixtral-8x7b-instruct-v0:1","max_context_window":32000,"input_cost":0.45,"output_cost":0.7,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.mixtral-8x7b-instruct-v0:1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.voxtral-mini-3b-2507","base_model_name":"bedrock/mistral.voxtral-mini-3b-2507","max_context_window":32000,"input_cost":0.04,"output_cost":0.04,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.voxtral-mini-3b-2507","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/mistral.voxtral-small-24b-2507","base_model_name":"bedrock/mistral.voxtral-small-24b-2507","max_context_window":32000,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/mistral.voxtral-small-24b-2507","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/moonshot.kimi-k2-thinking","base_model_name":"bedrock/moonshot.kimi-k2-thinking","max_context_window":256000,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/moonshot.kimi-k2-thinking","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/moonshotai.kimi-k2.5","base_model_name":"bedrock/moonshotai.kimi-k2.5","max_context_window":256000,"input_cost":0.6,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/moonshotai.kimi-k2.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/nvidia.nemotron-nano-12b-v2","base_model_name":"bedrock/nvidia.nemotron-nano-12b-v2","max_context_window":128000,"input_cost":0.2,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/nvidia.nemotron-nano-12b-v2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/nvidia.nemotron-nano-3-30b","base_model_name":"bedrock/nvidia.nemotron-nano-3-30b","max_context_window":256000,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/nvidia.nemotron-nano-3-30b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/nvidia.nemotron-nano-9b-v2","base_model_name":"bedrock/nvidia.nemotron-nano-9b-v2","max_context_window":128000,"input_cost":0.06,"output_cost":0.23,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/nvidia.nemotron-nano-9b-v2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/nvidia.nemotron-super-3-120b","base_model_name":"bedrock/nvidia.nemotron-super-3-120b","max_context_window":256000,"input_cost":0.15,"output_cost":0.65,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/nvidia.nemotron-super-3-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/openai.gpt-oss-120b-1:0","base_model_name":"bedrock/openai.gpt-oss-120b-1:0","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["bedrock/openai.gpt-oss-120b-1:0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"bedrock/openai.gpt-oss-120b-1:0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":43.3029,"average_ttft":2.5927,"average_latency":99.4993,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":43.3029,"average_ttft":2.5927,"average_latency":99.4993,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/openai.gpt-oss-20b-1:0","base_model_name":"bedrock/openai.gpt-oss-20b-1:0","max_context_window":131072,"input_cost":0.07,"output_cost":0.3,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["bedrock/openai.gpt-oss-20b-1:0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"bedrock/openai.gpt-oss-20b-1:0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":368.7082,"average_ttft":null,"average_latency":13.9831,"uptime_percent":99.7041,"cache_hit_percentage":0},"throughput":{"average_tps":368.7082,"average_ttft":null,"average_latency":13.9831,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/openai.gpt-oss-safeguard-120b","base_model_name":"bedrock/openai.gpt-oss-safeguard-120b","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/openai.gpt-oss-safeguard-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/openai.gpt-oss-safeguard-20b","base_model_name":"bedrock/openai.gpt-oss-safeguard-20b","max_context_window":128000,"input_cost":0.07,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/openai.gpt-oss-safeguard-20b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/qwen.qwen3-32b-v1:0","base_model_name":"bedrock/qwen.qwen3-32b-v1:0","max_context_window":32000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/qwen.qwen3-32b-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/qwen.qwen3-coder-30b-a3b-v1:0","base_model_name":"bedrock/qwen.qwen3-coder-30b-a3b-v1:0","max_context_window":256000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/qwen.qwen3-coder-30b-a3b-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/qwen.qwen3-coder-480b-a35b-v1:0","base_model_name":"bedrock/qwen.qwen3-coder-480b-a35b-v1:0","max_context_window":128000,"input_cost":0.45,"output_cost":1.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/qwen.qwen3-coder-480b-a35b-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.amazon.nova-2-lite-v1:0","base_model_name":"bedrock/us.amazon.nova-2-lite-v1:0","max_context_window":1000000,"input_cost":0.33,"output_cost":2.75,"cache_hit_input_cost":0.0825,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.amazon.nova-2-lite-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.amazon.nova-lite-v1:0","base_model_name":"bedrock/us.amazon.nova-lite-v1:0","max_context_window":300000,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.amazon.nova-lite-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.amazon.nova-micro-v1:0","base_model_name":"bedrock/us.amazon.nova-micro-v1:0","max_context_window":128000,"input_cost":0.035,"output_cost":0.14,"cache_hit_input_cost":0.00875,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.amazon.nova-micro-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.amazon.nova-pro-v1:0","base_model_name":"bedrock/us.amazon.nova-pro-v1:0","max_context_window":300000,"input_cost":0.8,"output_cost":3.2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.amazon.nova-pro-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-fable-5","base_model_name":"bedrock/us.anthropic.claude-fable-5","max_context_window":1000000,"input_cost":11,"output_cost":55,"cache_hit_input_cost":1.1,"cache_creation_input_cost":13.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-fable-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-fable-5-1","base_model_name":"bedrock/us.anthropic.claude-fable-5-1","max_context_window":1000000,"input_cost":11,"output_cost":55,"cache_hit_input_cost":0.275,"cache_creation_input_cost":13.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-fable-5-1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0","base_model_name":"bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-10-01","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0","base_model_name":"bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0","max_context_window":200000,"input_cost":15,"output_cost":75,"cache_hit_input_cost":1.5,"cache_creation_input_cost":18.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}},"context_size":200000,"release_date":"2025-08-05","prompt_logging":false,"expiration_date":"2027-01-08","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0","base_model_name":"bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0","max_context_window":200000,"input_cost":5.5,"output_cost":27.5,"cache_hit_input_cost":0.55,"cache_creation_input_cost":6.875,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-opus-4-5-20251101-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-4-7","base_model_name":"bedrock/us.anthropic.claude-opus-4-7","max_context_window":1000000,"input_cost":5.5,"output_cost":27.5,"cache_hit_input_cost":0.55,"cache_creation_input_cost":6.875,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-opus-4-7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-4-8","base_model_name":"bedrock/us.anthropic.claude-opus-4-8","max_context_window":1000000,"input_cost":5.5,"output_cost":27.5,"cache_hit_input_cost":0.55,"cache_creation_input_cost":6.875,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-opus-4-8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-5","base_model_name":"bedrock/us.anthropic.claude-opus-5","max_context_window":1000000,"input_cost":5.5,"output_cost":27.5,"cache_hit_input_cost":0.55,"cache_creation_input_cost":6.875,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-opus-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-opus-5-5","base_model_name":"bedrock/us.anthropic.claude-opus-5-5","max_context_window":1000000,"input_cost":4.4,"output_cost":22,"cache_hit_input_cost":0.22,"cache_creation_input_cost":5.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-opus-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0","base_model_name":"bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-sonnet-4-20250514-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0","base_model_name":"bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":["bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"context_size":200000,"release_date":"2025-09-29","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.2783,"average_ttft":null,"average_latency":3.5463,"uptime_percent":100,"cache_hit_percentage":22.0201},"throughput":{"average_tps":23.2783,"average_ttft":null,"average_latency":3.5463,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-sonnet-5","base_model_name":"bedrock/us.anthropic.claude-sonnet-5","max_context_window":1000000,"input_cost":2.2,"output_cost":11,"cache_hit_input_cost":0.22,"cache_creation_input_cost":2.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-sonnet-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.anthropic.claude-sonnet-5-5","base_model_name":"bedrock/us.anthropic.claude-sonnet-5-5","max_context_window":1000000,"input_cost":2.2,"output_cost":11,"cache_hit_input_cost":0.22,"cache_creation_input_cost":2.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.anthropic.claude-sonnet-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.deepseek.r1-v1:0","base_model_name":"bedrock/us.deepseek.r1-v1:0","max_context_window":128000,"input_cost":1.35,"output_cost":5.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.deepseek.r1-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.meta.llama3-1-70b-instruct-v1:0","base_model_name":"bedrock/us.meta.llama3-1-70b-instruct-v1:0","max_context_window":128000,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.meta.llama3-1-70b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.meta.llama3-1-8b-instruct-v1:0","base_model_name":"bedrock/us.meta.llama3-1-8b-instruct-v1:0","max_context_window":128000,"input_cost":0.22,"output_cost":0.22,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.meta.llama3-1-8b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.meta.llama3-3-70b-instruct-v1:0","base_model_name":"bedrock/us.meta.llama3-3-70b-instruct-v1:0","max_context_window":128000,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.meta.llama3-3-70b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.meta.llama4-maverick-17b-instruct-v1:0","base_model_name":"bedrock/us.meta.llama4-maverick-17b-instruct-v1:0","max_context_window":1000000,"input_cost":0.24,"output_cost":0.97,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.meta.llama4-maverick-17b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.meta.llama4-scout-17b-instruct-v1:0","base_model_name":"bedrock/us.meta.llama4-scout-17b-instruct-v1:0","max_context_window":10000000,"input_cost":0.17,"output_cost":0.66,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.meta.llama4-scout-17b-instruct-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.mistral.pixtral-large-2502-v1:0","base_model_name":"bedrock/us.mistral.pixtral-large-2502-v1:0","max_context_window":128000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.mistral.pixtral-large-2502-v1:0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.moonshotai.kimi-k3","base_model_name":"bedrock/us.moonshotai.kimi-k3","max_context_window":1000000,"input_cost":3.3,"output_cost":16.5,"cache_hit_input_cost":0.33,"cache_creation_input_cost":4.125,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.moonshotai.kimi-k3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-5.6-luna","base_model_name":"bedrock/us.openai.gpt-5.6-luna","max_context_window":1050000,"input_cost":0.22,"output_cost":1.32,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0.275,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-5.6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-5.6-sol","base_model_name":"bedrock/us.openai.gpt-5.6-sol","max_context_window":1050000,"input_cost":4.4,"output_cost":22,"cache_hit_input_cost":0.44,"cache_creation_input_cost":5.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-5.6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-5.6-terra","base_model_name":"bedrock/us.openai.gpt-5.6-terra","max_context_window":1050000,"input_cost":2.2,"output_cost":13.2,"cache_hit_input_cost":0.22,"cache_creation_input_cost":2.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-5.6-terra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-6-astra","base_model_name":"bedrock/us.openai.gpt-6-astra","max_context_window":1050000,"input_cost":11,"output_cost":55,"cache_hit_input_cost":1.1,"cache_creation_input_cost":13.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-6-astra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-6-luna","base_model_name":"bedrock/us.openai.gpt-6-luna","max_context_window":1050000,"input_cost":0.11,"output_cost":0.55,"cache_hit_input_cost":0.011,"cache_creation_input_cost":0.1375,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-6-sol","base_model_name":"bedrock/us.openai.gpt-6-sol","max_context_window":1050000,"input_cost":2.2,"output_cost":11,"cache_hit_input_cost":0.22,"cache_creation_input_cost":2.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/us.openai.gpt-6.1-sol","base_model_name":"bedrock/us.openai.gpt-6.1-sol","max_context_window":1000000,"input_cost":2.2,"output_cost":11,"cache_hit_input_cost":0.11,"cache_creation_input_cost":2.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/us.openai.gpt-6.1-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/writer.palmyra-vision-7b","base_model_name":"bedrock/writer.palmyra-vision-7b","max_context_window":4000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/writer.palmyra-vision-7b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/zai.glm-4.7","base_model_name":"bedrock/zai.glm-4.7","max_context_window":203000,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/zai.glm-4.7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/zai.glm-4.7-flash","base_model_name":"bedrock/zai.glm-4.7-flash","max_context_window":203000,"input_cost":0.07,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/zai.glm-4.7-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Bedrock","provider_id":"bedrock","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.168443Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://bedrock.us-west-2.amazonaws.com"},"kind":"host","id":"bedrock"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"bedrock/zai.glm-5","base_model_name":"bedrock/zai.glm-5","max_context_window":200000,"input_cost":1,"output_cost":3.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"bedrock/zai.glm-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cerebras","provider_id":"cerebras","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.281570Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cerebras.ai/v1/models"},"kind":"host","id":"cerebras"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"cerebras/gpt-oss-120b","base_model_name":"gpt-oss-120b","max_context_window":131072,"input_cost":0.35,"output_cost":0.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"cerebras/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cerebras","provider_id":"cerebras","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.281570Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cerebras.ai/v1/models"},"kind":"host","id":"cerebras"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"cerebras/qwen-3.8-27b","base_model_name":"cerebras/qwen-3.8-27b","max_context_window":131072,"input_cost":0.99,"output_cost":1.49,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-03"},"id":"cerebras/qwen-3.8-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"chutes/deepseek-ai/DeepSeek-V3.2-TEE","base_model_name":"deepseek-ai/DeepSeek-V3.2-TEE","max_context_window":131072,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/deepseek-ai/DeepSeek-V3.2-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.7903,"average_ttft":null,"average_latency":3.4539,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.7903,"average_ttft":null,"average_latency":3.4539,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE","base_model_name":"","max_context_window":1048576,"input_cost":0.44,"output_cost":1.32,"cache_hit_input_cost":0.04399999999999999,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/deepseek-ai/DeepSeek-V4-Flash-0731-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/google/gemma-4-31B-turbo-TEE","base_model_name":"","max_context_window":131072,"input_cost":0.12,"output_cost":0.37,"cache_hit_input_cost":0.011999999999999997,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/google/gemma-4-31B-turbo-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/moonshotai/Kimi-K2.6-TEE","base_model_name":"","max_context_window":262144,"input_cost":0.5,"output_cost":2.85,"cache_hit_input_cost":0.04999999999999999,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/moonshotai/Kimi-K2.6-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/moonshotai/Kimi-K3-TEE","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.29999999999999993,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/moonshotai/Kimi-K3-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/Nemotron-3-Nano-Omni-30B-TEE","base_model_name":"","max_context_window":4096,"input_cost":0.0245,"output_cost":0.0978,"cache_hit_input_cost":0.0024499999999999995,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/Nemotron-3-Nano-Omni-30B-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.4882,"average_ttft":null,"average_latency":1.6086,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.4882,"average_ttft":null,"average_latency":1.6086,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","base_model_name":"","max_context_window":262144,"input_cost":0.2989,"output_cost":1.1957,"cache_hit_input_cost":0.029889999999999993,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/Qwen/Qwen3-235B-A22B-Thinking-2507-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"chutes/Qwen/Qwen3-32B-TEE","base_model_name":"Qwen/Qwen3-32B-TEE","max_context_window":40960,"input_cost":0.104,"output_cost":0.416,"cache_hit_input_cost":0.0104,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","input_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"chutes/Qwen/Qwen3-32B-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.7529,"average_ttft":null,"average_latency":4.1633,"uptime_percent":100,"cache_hit_percentage":0.4247},"throughput":{"average_tps":23.7529,"average_ttft":null,"average_latency":4.1633,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/Qwen/Qwen3.5-397B-A17B-TEE","base_model_name":"","max_context_window":262144,"input_cost":0.45,"output_cost":3,"cache_hit_input_cost":0.04499999999999999,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/Qwen/Qwen3.5-397B-A17B-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/Qwen/Qwen3.6-27B-TEE","base_model_name":"","max_context_window":262144,"input_cost":0.3,"output_cost":2,"cache_hit_input_cost":0.029999999999999992,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/Qwen/Qwen3.6-27B-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/Qwen/Qwen3.8-27B-TEE","base_model_name":"","max_context_window":262144,"input_cost":0.24,"output_cost":2.2,"cache_hit_input_cost":0.023999999999999994,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/Qwen/Qwen3.8-27B-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE","base_model_name":"","max_context_window":4096,"input_cost":0.0245,"output_cost":0.0978,"cache_hit_input_cost":0.0024499999999999995,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"chutes/unsloth/Mistral-Nemo-Instruct-2407-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":2.5191,"average_ttft":null,"average_latency":1.1909,"uptime_percent":100,"cache_hit_percentage":18.1818},"throughput":{"average_tps":2.5191,"average_ttft":null,"average_latency":1.1909,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"chutes/zai-org/GLM-5.1-TEE","base_model_name":"zai-org/GLM-5.1-TEE","max_context_window":202752,"input_cost":0.98,"output_cost":3.08,"cache_hit_input_cost":0.09799999999999998,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-01"},"id":"chutes/zai-org/GLM-5.1-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.5919,"average_ttft":null,"average_latency":40.871,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.5919,"average_ttft":null,"average_latency":40.871,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Chutes","provider_id":"chutes","extra_kwargs":{},"created_at":"2026-06-08T22:36:32.836613Z","updated_at":"2026-06-12T04:02:09.952206Z","respan_discount_rate":0.05,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://llm.chutes.ai/v1/models"},"kind":"host","id":"chutes"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"chutes/zai-org/GLM-5.2-TEE","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":3.95,"cache_hit_input_cost":0.12499999999999997,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-13"},"id":"chutes/zai-org/GLM-5.2-TEE","is_byok":false,"effective_discount_rate":0.05,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/c4ai-aya-expanse-32b","base_model_name":"c4ai-aya-expanse-32b","max_context_window":128000,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-24"},"id":"cohere/c4ai-aya-expanse-32b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.8912,"average_ttft":null,"average_latency":0.6836,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.8912,"average_ttft":null,"average_latency":0.6836,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-a-03-2025","base_model_name":"command-a-03-2025","max_context_window":288000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"cohere/command-a-03-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.43,"average_ttft":null,"average_latency":0.4672,"uptime_percent":91.6667,"cache_hit_percentage":0},"throughput":{"average_tps":35.43,"average_ttft":null,"average_latency":0.4672,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-a-reasoning-08-2025","base_model_name":"command-a-reasoning-08-2025","max_context_window":288768,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-21"},"id":"cohere/command-a-reasoning-08-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":96.5738,"average_ttft":null,"average_latency":2.1738,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":96.5738,"average_ttft":null,"average_latency":2.1738,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-a-vision-07-2025","base_model_name":"command-a-vision-07-2025","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-31"},"id":"cohere/command-a-vision-07-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.7441,"average_ttft":null,"average_latency":0.7342,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.7441,"average_ttft":null,"average_latency":0.7342,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-r-08-2024","base_model_name":"command-r-08-2024","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-03-11"},"id":"cohere/command-r-08-2024","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.1156,"average_ttft":null,"average_latency":0.3122,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.1156,"average_ttft":null,"average_latency":0.3122,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-r-plus-08-2024","base_model_name":"command-r-plus-08-2024","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-03-11"},"id":"cohere/command-r-plus-08-2024","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":14.2712,"average_ttft":null,"average_latency":0.8039,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.2712,"average_ttft":null,"average_latency":0.8039,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-r7b-12-2024","base_model_name":"command-r7b-12-2024","max_context_window":132000,"input_cost":0.0375,"output_cost":0.15,"cache_hit_input_cost":0.0038,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-03-11"},"id":"cohere/command-r7b-12-2024","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":41.8292,"average_ttft":null,"average_latency":0.2734,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":41.8292,"average_ttft":null,"average_latency":0.2734,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"cohere/command-r7b-arabic-02-2025","base_model_name":"command-r7b-arabic-02-2025","max_context_window":128000,"input_cost":0.0375,"output_cost":0.15,"cache_hit_input_cost":0.0038,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-03-11"},"id":"cohere/command-r7b-arabic-02-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.9,"average_ttft":null,"average_latency":300.5558,"uptime_percent":71.4286,"cache_hit_percentage":0},"throughput":{"average_tps":17.9,"average_ttft":null,"average_latency":0.3005558,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Cohere","provider_id":"cohere","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.613924Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.cohere.com/v1/models"},"kind":"host","id":"cohere"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"cohere/embed-english-v3.0","base_model_name":"embed-english-v3.0","max_context_window":8191,"input_cost":0.1,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"cohere/embed-english-v3.0","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-fable-5","base_model_name":"","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}}},"id":"deepinfra/anthropic/claude-fable-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-haiku-4-5","base_model_name":"","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/anthropic/claude-haiku-4-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-opus-4-7","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/anthropic/claude-opus-4-7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-opus-4-8","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}}},"id":"deepinfra/anthropic/claude-opus-4-8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-opus-5","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7752095907502038,"ci_lo":0.6977633822227692,"model":"claude-opus-5","config":"mini_swe_agent_claude_opus_5_max","n_runs":4,"source":"deep-swe","ci_half":0.03872310426371729,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7364864864864865,"pass_at_4":0.8849557522123894,"pass_rate":0.7364864864864865,"n_attempted":444,"ci_attempted":444,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":11.837583271396396,"n_tasks_in_set":113,"median_cost_usd":10.4281505,"mean_agent_steps":99.0427927927928,"reasoning_effort":"max","mean_cache_tokens":14784785.963963963,"mean_input_tokens":15025834.39864865,"n_tasks_attempted":113,"mean_output_tokens":117565.6936936937,"median_agent_steps":90.5,"n_tasks_passed_any":100,"median_input_tokens":12130307.5,"median_output_tokens":113366.5,"mean_duration_seconds":1911.819866231982,"median_duration_seconds":1801.1237265,"median_peak_context_tokens":215810,"median_output_tokens_to_pass":112874}}},"id":"deepinfra/anthropic/claude-opus-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-opus-5-5","base_model_name":"","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/anthropic/claude-opus-5-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-sonnet-4-6","base_model_name":"","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}}},"id":"deepinfra/anthropic/claude-sonnet-4-6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-sonnet-5","base_model_name":"","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}}},"id":"deepinfra/anthropic/claude-sonnet-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/anthropic/claude-sonnet-5-5","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/anthropic/claude-sonnet-5-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-R1-0528","base_model_name":"deepinfra/deepseek-ai/DeepSeek-R1-0528","max_context_window":163840,"input_cost":0.5,"output_cost":2.15,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/deepseek-ai/DeepSeek-R1-0528","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.5122,"average_ttft":null,"average_latency":3.1687,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.5122,"average_ttft":null,"average_latency":3.1687,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V3","base_model_name":"","max_context_window":163840,"input_cost":0.32,"output_cost":0.89,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/deepseek-ai/DeepSeek-V3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V3.1","base_model_name":"","max_context_window":163840,"input_cost":0.25,"output_cost":0.95,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/deepseek-ai/DeepSeek-V3.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V3.2","base_model_name":"deepinfra/deepseek-ai/DeepSeek-V3.2","max_context_window":163840,"input_cost":0.26,"output_cost":0.38,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/deepseek-ai/DeepSeek-V3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.6599,"average_ttft":null,"average_latency":2.8108,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.6599,"average_ttft":null,"average_latency":2.8108,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.09,"output_cost":0.18,"cache_hit_input_cost":0.018,"cache_creation_input_cost":0.1125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}}},"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","max_context_window":1048576,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"is_available_on_credits":true},"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.1477,"average_ttft":0.9024,"average_latency":0.8868,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.1477,"average_ttft":0.9024,"average_latency":0.8868,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","base_model_name":"","max_context_window":1048576,"input_cost":0.44,"output_cost":1.32,"cache_hit_input_cost":0.014,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/deepseek-ai/DeepSeek-V4-Flash-Vision-Exp","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"","max_context_window":1048576,"input_cost":1.3,"output_cost":2.6,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","max_context_window":1048576,"input_cost":1.3,"output_cost":2.6,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"is_available_on_credits":true},"id":"deepinfra/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.386,"average_ttft":null,"average_latency":0.3059,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.386,"average_ttft":null,"average_latency":0.3059,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.2,"output_cost":0.6,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-2.5-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemini-2.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-2.5-pro","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemini-2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-3.1-flash-lite","base_model_name":"","max_context_window":1000000,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemini-3.1-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-3.1-pro","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemini-3.1-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-3.5-flash","base_model_name":"","max_context_window":1000000,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}}},"id":"deepinfra/google/gemini-3.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemini-3.7-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}}},"id":"deepinfra/google/gemini-3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-3-12b-it","base_model_name":"","max_context_window":131072,"input_cost":0.05,"output_cost":0.15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemma-3-12b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-3-27b-it","base_model_name":"","max_context_window":131072,"input_cost":0.08,"output_cost":0.16,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-3-4b-it","base_model_name":"","max_context_window":131072,"input_cost":0.05,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemma-3-4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-4-26B-A4B-it","base_model_name":"deepinfra/google/gemma-4-26B-A4B-it","max_context_window":262144,"input_cost":0.07,"output_cost":0.34,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/google/gemma-4-26B-A4B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":54.4943,"average_ttft":0.6617,"average_latency":1.2877,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":54.4943,"average_ttft":0.6617,"average_latency":1.2877,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-4-31B-it","base_model_name":"deepinfra/google/gemma-4-31B-it","max_context_window":262144,"input_cost":0.13,"output_cost":0.38,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/google/gemma-4-31B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.7697,"average_ttft":0.5863,"average_latency":3.8067,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.7697,"average_ttft":0.5863,"average_latency":3.8067,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-4-31B-it-turbo","base_model_name":"","max_context_window":262144,"input_cost":0.09,"output_cost":0.34,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-03"},"id":"deepinfra/google/gemma-4-31B-it-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-4-31B-it-Ultra","base_model_name":"","max_context_window":131072,"input_cost":0.27,"output_cost":0.76,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-03"},"id":"deepinfra/google/gemma-4-31B-it-Ultra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/google/gemma-4-E4B-it","base_model_name":"","max_context_window":131072,"input_cost":0.02,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/google/gemma-4-E4B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Gryphe/MythoMax-L2-13b","base_model_name":"","max_context_window":4096,"input_cost":0.4,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Gryphe/MythoMax-L2-13b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/ibm-granite/granite-4.2-30b","base_model_name":"","max_context_window":131072,"input_cost":0.16,"output_cost":0.65,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-25"},"id":"deepinfra/ibm-granite/granite-4.2-30b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/ibm-granite/granite-4.2-3b","base_model_name":"","max_context_window":131072,"input_cost":0.03,"output_cost":0.12,"cache_hit_input_cost":0.0075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-25"},"id":"deepinfra/ibm-granite/granite-4.2-3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/ibm-granite/granite-4.2-8b","base_model_name":"","max_context_window":131072,"input_cost":0.06,"output_cost":0.25,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-25"},"id":"deepinfra/ibm-granite/granite-4.2-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/inclusionAI/Ling-3.0-flash","base_model_name":"","max_context_window":131072,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/inclusionAI/Ling-3.0-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/inclusionAI/Ling-3.0-flash-Fin","base_model_name":"","max_context_window":262144,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/inclusionAI/Ling-3.0-flash-Fin","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/inclusionAI/Ling-3.0-flash-VL","base_model_name":"","max_context_window":131072,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/inclusionAI/Ling-3.0-flash-VL","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","base_model_name":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","max_context_window":131072,"input_cost":0.1,"output_cost":0.32,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.2272,"average_ttft":null,"average_latency":1.3992,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.2272,"average_ttft":null,"average_latency":1.3992,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","base_model_name":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","max_context_window":1048576,"input_cost":0.2,"output_cost":0.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.5149,"average_ttft":null,"average_latency":0.4228,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.5149,"average_ttft":null,"average_latency":0.4228,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","base_model_name":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","max_context_window":327680,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":32.4239,"average_ttft":null,"average_latency":0.388,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.4239,"average_ttft":null,"average_latency":0.388,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","base_model_name":"","max_context_window":131072,"input_cost":0.4,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","base_model_name":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","max_context_window":131072,"input_cost":0.02,"output_cost":0.04,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-23","is_available_on_credits":true},"id":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.6353,"average_ttft":null,"average_latency":0.5545,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.6353,"average_ttft":null,"average_latency":0.5545,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/meta-models/Muse-Glimmer-30B","base_model_name":"","max_context_window":131072,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/meta-models/Muse-Glimmer-30B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/microsoft/phi-4","base_model_name":"","max_context_window":16384,"input_cost":0.07,"output_cost":0.14,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/microsoft/phi-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/MiniMaxAI/MiniMax-M3","base_model_name":"deepinfra/MiniMaxAI/MiniMax-M3","max_context_window":524288,"input_cost":0.28,"output_cost":1.1,"cache_hit_input_cost":0.056,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/MiniMaxAI/MiniMax-M3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.5405,"average_ttft":null,"average_latency":41.5848,"uptime_percent":100,"cache_hit_percentage":70.8487},"throughput":{"average_tps":6.5405,"average_ttft":null,"average_latency":41.5848,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","base_model_name":"","max_context_window":131072,"input_cost":0.019,"output_cost":0.03,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/mistralai/Mistral-Nemo-Instruct-2407","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","base_model_name":"","max_context_window":32768,"input_cost":0.05,"output_cost":0.08,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/mistralai/Mistral-Small-24B-Instruct-2501","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","base_model_name":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","max_context_window":128000,"input_cost":0.075,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":24.7322,"average_ttft":null,"average_latency":0.5626,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.7322,"average_ttft":null,"average_latency":0.5626,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/moonshotai/Kimi-K2.6","base_model_name":"","max_context_window":262144,"input_cost":0.75,"output_cost":3.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/moonshotai/Kimi-K2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/moonshotai/Kimi-K3","base_model_name":"deepinfra/moonshotai/Kimi-K3","max_context_window":1048576,"input_cost":2.85,"output_cost":14.25,"cache_hit_input_cost":0.285,"cache_creation_input_cost":3.5625,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"is_available_on_credits":true},"id":"deepinfra/moonshotai/Kimi-K3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.8893,"average_ttft":null,"average_latency":65.1462,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.8893,"average_ttft":null,"average_latency":65.1462,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","base_model_name":"","max_context_window":131072,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-405B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","base_model_name":"","max_context_window":131072,"input_cost":0.7,"output_cost":0.7,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/NousResearch/Hermes-3-Llama-3.1-70B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","base_model_name":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","max_context_window":262144,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/nvidia/Nemotron-3-Nano-30B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":55.5051,"average_ttft":null,"average_latency":1.4615,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":55.5051,"average_ttft":null,"average_latency":1.4615,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","base_model_name":"","max_context_window":262144,"input_cost":0.085,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-11"},"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","base_model_name":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","max_context_window":262144,"input_cost":0.5,"output_cost":2.2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0.625,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-04","is_available_on_credits":true},"id":"deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":38.5669,"average_ttft":null,"average_latency":1.1181,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.5669,"average_ttft":null,"average_latency":1.1181,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","base_model_name":"","max_context_window":262144,"input_cost":0.06,"output_cost":0.16,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-11"},"id":"deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/openai/gpt-oss-120b","base_model_name":"deepinfra/openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.037,"output_cost":0.17,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.035,"average_ttft":null,"average_latency":43.0554,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.035,"average_ttft":null,"average_latency":43.0554,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/openai/gpt-oss-120b-Turbo","base_model_name":"","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"deepinfra/openai/gpt-oss-120b-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/openai/gpt-oss-120b-Ultra","base_model_name":"","max_context_window":131072,"input_cost":0.2,"output_cost":0.95,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"deepinfra/openai/gpt-oss-120b-Ultra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/openai/gpt-oss-20b","base_model_name":"deepinfra/openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.03,"output_cost":0.14,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":55.5656,"average_ttft":null,"average_latency":1.2026,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":55.5656,"average_ttft":null,"average_latency":1.2026,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen2.5-72B-Instruct","base_model_name":"","max_context_window":32768,"input_cost":0.36,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen2.5-72B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-14B","base_model_name":"","max_context_window":40960,"input_cost":0.12,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3-14B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","base_model_name":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","max_context_window":262144,"input_cost":0.09,"output_cost":0.55,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":14.709,"average_ttft":null,"average_latency":0.6461,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.709,"average_ttft":null,"average_latency":0.6461,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-30B-A3B","base_model_name":"","max_context_window":40960,"input_cost":0.12,"output_cost":0.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3-30B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-32B","base_model_name":"deepinfra/Qwen/Qwen3-32B","max_context_window":40960,"input_cost":0.08,"output_cost":0.28,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3-32B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.0516,"average_ttft":null,"average_latency":4.3571,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.0516,"average_ttft":null,"average_latency":4.3571,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","base_model_name":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","max_context_window":262144,"input_cost":0.3,"output_cost":1,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-23","is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.9018,"average_ttft":null,"average_latency":2.3759,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.9018,"average_ttft":null,"average_latency":2.3759,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","base_model_name":"","max_context_window":262144,"input_cost":0.09,"output_cost":1.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","base_model_name":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","max_context_window":262144,"input_cost":0.2,"output_cost":0.88,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.8867,"average_ttft":null,"average_latency":1.9151,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.8867,"average_ttft":null,"average_latency":1.9151,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","base_model_name":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.8526,"average_ttft":null,"average_latency":23.332,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.8526,"average_ttft":null,"average_latency":23.332,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.5-122B-A10B","base_model_name":"","max_context_window":262144,"input_cost":0.29,"output_cost":2.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.5-122B-A10B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.5-27B","base_model_name":"","max_context_window":262144,"input_cost":0.26,"output_cost":2.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.5-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.5-35B-A3B","base_model_name":"","max_context_window":262144,"input_cost":0.14,"output_cost":1,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.5-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.5-397B-A17B","base_model_name":"deepinfra/Qwen/Qwen3.5-397B-A17B","max_context_window":262144,"input_cost":0.45,"output_cost":3,"cache_hit_input_cost":0.22,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3.5-397B-A17B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":47.0386,"average_ttft":null,"average_latency":2.1314,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":47.0386,"average_ttft":null,"average_latency":2.1314,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.5-9B","base_model_name":"","max_context_window":262144,"input_cost":0.1,"output_cost":0.15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.5-9B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.6-27B","base_model_name":"","max_context_window":262144,"input_cost":0.32,"output_cost":3.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.6-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.6-35B-A3B","base_model_name":"deepinfra/Qwen/Qwen3.6-35B-A3B","max_context_window":262144,"input_cost":0.1,"output_cost":0.95,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3.6-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":81.3151,"average_ttft":null,"average_latency":1.3126,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":81.3151,"average_ttft":null,"average_latency":1.3126,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.8-2.4T-A95B","base_model_name":"deepinfra/Qwen/Qwen3.8-2.4T-A95B","max_context_window":262144,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-12","is_available_on_credits":true},"id":"deepinfra/Qwen/Qwen3.8-2.4T-A95B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":40.0181,"average_ttft":null,"average_latency":0.8052,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":40.0181,"average_ttft":null,"average_latency":0.8052,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.8-27B","base_model_name":"","max_context_window":262144,"input_cost":0.2,"output_cost":2.5,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.8-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.8-Flash","base_model_name":"","max_context_window":1000000,"input_cost":0.113,"output_cost":0.382,"cache_hit_input_cost":0.0141,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Qwen/Qwen3.8-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Qwen/Qwen3.8-Max","base_model_name":"","max_context_window":256000,"input_cost":1.65,"output_cost":4.951,"cache_hit_input_cost":0.206,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}}},"id":"deepinfra/Qwen/Qwen3.8-Max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","base_model_name":"","max_context_window":8192,"input_cost":0.04,"output_cost":0.05,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-08-13"},"id":"deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","base_model_name":"","max_context_window":131072,"input_cost":0.85,"output_cost":0.85,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/Sao10K/L3.1-70B-Euryale-v2.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/stepfun-ai/Step-3.7-Flash","base_model_name":"","max_context_window":262144,"input_cost":0.2,"output_cost":1.15,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/stepfun-ai/Step-3.7-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/tencent/Hy3","base_model_name":"","max_context_window":262144,"input_cost":0.13,"output_cost":0.53,"cache_hit_input_cost":0.033,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/tencent/Hy3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/tencent/Hy4-preview","base_model_name":"","max_context_window":1048576,"input_cost":0.834,"output_cost":2.501,"cache_hit_input_cost":0.042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/tencent/Hy4-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/thinkingmachines/Inkling","base_model_name":"","max_context_window":524288,"input_cost":0.95,"output_cost":4.05,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/thinkingmachines/Inkling","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/thinkingmachines/Inkling-Small","base_model_name":"","max_context_window":524288,"input_cost":0.45,"output_cost":1.2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/thinkingmachines/Inkling-Small","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/XiaomiMiMo/MiMo-V2.6-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.0028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/XiaomiMiMo/MiMo-V2.6-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/XiaomiMiMo/MiMo-V2.6-Pro","base_model_name":"","max_context_window":1048576,"input_cost":0.43,"output_cost":0.87,"cache_hit_input_cost":0.0036,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/XiaomiMiMo/MiMo-V2.6-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-4.6","base_model_name":"","max_context_window":202752,"input_cost":0.5,"output_cost":2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/zai-org/GLM-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-4.7","base_model_name":"deepinfra/zai-org/GLM-4.7","max_context_window":202752,"input_cost":0.4,"output_cost":1.75,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"deepinfra/zai-org/GLM-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.357,"average_ttft":null,"average_latency":8.9502,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.357,"average_ttft":null,"average_latency":8.9502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-5.1","base_model_name":"","max_context_window":202752,"input_cost":1.05,"output_cost":3.5,"cache_hit_input_cost":0.205,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"deepinfra/zai-org/GLM-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-5.2","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":2.4,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0.9375,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"deepinfra/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-5.3","base_model_name":"deepinfra/zai-org/GLM-5.3","max_context_window":1048576,"input_cost":0.9,"output_cost":4,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"is_available_on_credits":true},"id":"deepinfra/zai-org/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.0865,"average_ttft":null,"average_latency":18.1873,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.0865,"average_ttft":null,"average_latency":18.1873,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"DeepInfra","provider_id":"deepinfra","extra_kwargs":{},"created_at":"2026-09-09T08:34:16.993745Z","updated_at":"2026-09-09T08:34:16.993763Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.deepinfra.com/models/list"},"kind":"host","id":"deepinfra"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepinfra/zai-org/GLM-5.3-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}}},"id":"deepinfra/zai-org/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Deepseek","provider_id":"deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.523289Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.deepseek.com/models"},"kind":"host","id":"deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":1,"required":false,"description":"Sampling temperature; ignored in thinking mode."},"max_tokens":{"name":"max_tokens","type":"int","range":{"max":393216,"min":1},"required":false,"description":"Maximum generated tokens, including reasoning. Defaults: non-thinking 8192; thinking 65536; max effort 131072. Input plus output must fit context."},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Must be greater than zero. Thinking mode clamps values below 0.95; non-thinking mode fixes it at 1."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Text or JSON object output. JSON mode requires a JSON instruction."},"reasoning_effort":{"name":"reasoning_effort","type":"string","default":"high","required":false,"description":"none disables thinking; low, high, max enable it. minimal maps to low; medium and xhigh map to high; ultra maps to max."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"deepseek/deepseek-flash","base_model_name":"deepseek/deepseek-flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"json_mode":1,"context_size":1048576,"release_date":"2026-09-10","max_output_length":393216,"reasoning_support":1,"response_api_support":true,"is_available_on_credits":true},"id":"deepseek/deepseek-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":169.2823,"average_ttft":2.1513,"average_latency":4.731,"uptime_percent":99.971,"cache_hit_percentage":98.5667},"throughput":{"average_tps":169.2823,"average_ttft":2.1513,"average_latency":4.731,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Deepseek","provider_id":"deepseek","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.523289Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.deepseek.com/models"},"kind":"host","id":"deepseek"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"deepseek/deepseek-v4-pro","base_model_name":"deepseek-v4-pro","max_context_window":1048576,"input_cost":0.435,"output_cost":0.87,"cache_hit_input_cost":0.003625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"context_size":1048576,"release_date":"2026-04","prompt_training":false},"id":"deepseek/deepseek-v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":67.9211,"average_ttft":0.7198,"average_latency":9.9455,"uptime_percent":99.9503,"cache_hit_percentage":16.3442},"throughput":{"average_tps":67.9211,"average_ttft":0.7198,"average_latency":9.9455,"number_of_requests":null},"benchmark":{"cost":0.24138687892256638,"intelligence":0.6283185840707964,"latency":2212.510104011062,"speed":47.90889675460797,"context":232374.5,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepreasoning","base_model_name":"","max_context_window":4096,"input_cost":4.8,"output_cost":23,"cache_hit_input_cost":4.8,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-26"},"id":"empiriolabs/deepreasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v3-2","base_model_name":"","max_context_window":128000,"input_cost":0.57,"output_cost":1.71,"cache_hit_input_cost":0.57,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-01"},"id":"empiriolabs/deepseek-v3-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v4-1-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"empiriolabs/deepseek-v4-1-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v4-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"empiriolabs/deepseek-v4-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":0.10023560370265487,"intelligence":0.5331858407079646,"latency":1438.9961937522125,"speed":74.83482068364452,"context":201636.5,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v4-flash-0731","base_model_name":"","max_context_window":1000000,"input_cost":0.424,"output_cost":1.272,"cache_hit_input_cost":0.424,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-31"},"id":"empiriolabs/deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v4-pro","base_model_name":"","max_context_window":1000000,"input_cost":1.65,"output_cost":3.3,"cache_hit_input_cost":1.65,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24"},"id":"empiriolabs/deepseek-v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":0.24138687892256638,"intelligence":0.6283185840707964,"latency":2212.510104011062,"speed":47.90889675460797,"context":232374.5,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/deepseek-v4-pro-0813","base_model_name":"","max_context_window":1000000,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":1.32,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-13"},"id":"empiriolabs/deepseek-v4-pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/fugu-max","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"empiriolabs/fugu-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/fugu-ultra-v1-0","base_model_name":"","max_context_window":1000000,"input_cost":7.5,"output_cost":45,"cache_hit_input_cost":1.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-21"},"id":"empiriolabs/fugu-ultra-v1-0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/fugu-ultra-v1-1","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-23"},"id":"empiriolabs/fugu-ultra-v1-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/fugu-ultra-v2-0","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"empiriolabs/fugu-ultra-v2-0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/gemma-4-26b-a4b","base_model_name":"empiriolabs/gemma-4-26b-a4b","max_context_window":262144,"input_cost":0.05,"output_cost":0.29,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-31","is_available_on_credits":true},"id":"empiriolabs/gemma-4-26b-a4b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":89.6558,"average_ttft":0.904,"average_latency":0.9502,"uptime_percent":100,"cache_hit_percentage":49.083},"throughput":{"average_tps":89.6558,"average_ttft":0.904,"average_latency":0.9502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/glm-5-1","base_model_name":"","max_context_window":202000,"input_cost":0.825,"output_cost":3.301,"cache_hit_input_cost":0.165,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"empiriolabs/glm-5-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/glm-5-2","base_model_name":"","max_context_window":1000000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":1.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16"},"id":"empiriolabs/glm-5-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":3.9199075743111114,"intelligence":0.43777777777777777,"latency":2629.2083211311115,"speed":29.733401510396437,"context":142129,"passAt4":0.7699115044247787}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/glm-5-3","base_model_name":"","max_context_window":1000000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":1.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-14"},"id":"empiriolabs/glm-5-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":3.9933584893126386,"intelligence":0.6895787139689579,"latency":2116.1784804168515,"speed":38.00984203385959,"context":144729,"passAt4":0.8761061946902655}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/glm-5-3-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.075,"output_cost":0.25,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"empiriolabs/glm-5-3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":55.0476,"average_ttft":null,"average_latency":204.9327,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":55.0476,"average_ttft":null,"average_latency":0.20493270000000002,"number_of_requests":null},"benchmark":{"cost":0.48196371245535713,"intelligence":0.6339285714285714,"latency":1537.7995419129463,"speed":47.35972934332461,"context":136183.5,"passAt4":0.8495575221238938}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/kimi-k2-6","base_model_name":"","max_context_window":256000,"input_cost":0.8939,"output_cost":3.7131,"cache_hit_input_cost":0.1788,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-20"},"id":"empiriolabs/kimi-k2-6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/kimi-k2-7-code","base_model_name":"","max_context_window":256000,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.95,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"release_date":"2026-06-16"},"id":"empiriolabs/kimi-k2-7-code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":2.815536243274336,"intelligence":0.3053097345132743,"latency":2163.7950712809734,"speed":27.40428082799286,"context":122628.5,"passAt4":0.6106194690265486}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/kimi-k2-7-code-highspeed","base_model_name":"","max_context_window":256000,"input_cost":1.9,"output_cost":8,"cache_hit_input_cost":1.9,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-16"},"id":"empiriolabs/kimi-k2-7-code-highspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/kimi-k3","base_model_name":"","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-15"},"id":"empiriolabs/kimi-k3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":4.654682129933482,"intelligence":0.6851441241685144,"latency":4541.447376412417,"speed":17.94578596140072,"context":130945,"passAt4":0.8938053097345132}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mimo-v2-5","base_model_name":"","max_context_window":1000000,"input_cost":0.7,"output_cost":1.4,"cache_hit_input_cost":0.014,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"empiriolabs/mimo-v2-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mimo-v2-5-pro","base_model_name":"","max_context_window":1000000,"input_cost":2.175,"output_cost":4.35,"cache_hit_input_cost":0.018,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"empiriolabs/mimo-v2-5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mimo-v2-6-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"empiriolabs/mimo-v2-6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mimo-v2-6-pro","base_model_name":"","max_context_window":1000000,"input_cost":0.435,"output_cost":0.87,"cache_hit_input_cost":0.435,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"empiriolabs/mimo-v2-6-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mimo-v2-6-pro-ultraspeed","base_model_name":"","max_context_window":1000000,"input_cost":4.35,"output_cost":8.7,"cache_hit_input_cost":4.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"empiriolabs/mimo-v2-6-pro-ultraspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/minimax-m2-7","base_model_name":"","max_context_window":200000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"empiriolabs/minimax-m2-7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/minimax-m2-7-highspeed","base_model_name":"","max_context_window":200000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"empiriolabs/minimax-m2-7-highspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/minimax-m3","base_model_name":"","max_context_window":1000000,"input_cost":0.225,"output_cost":0.9,"cache_hit_input_cost":0.045,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-01"},"id":"empiriolabs/minimax-m3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/mistral-small-4","base_model_name":"","max_context_window":256000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-16"},"id":"empiriolabs/mistral-small-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/muse-glimmer-30b","base_model_name":"","max_context_window":131072,"input_cost":0.2,"output_cost":0.8,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-10"},"id":"empiriolabs/muse-glimmer-30b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/muse-spark-1-1","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5635392652473017,"ci_lo":0.5028324161686275,"model":"muse-spark-1-1","config":"mini_swe_agent_muse_spark_1_1_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.030353424539337114,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.7964601769911505,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.361142644469026,"n_tasks_in_set":113,"median_cost_usd":1.7171158,"mean_agent_steps":95.82522123893806,"reasoning_effort":"xhigh","mean_cache_tokens":11781947.471238937,"mean_input_tokens":12005399.261061948,"n_tasks_attempted":113,"mean_output_tokens":74008.4203539823,"median_agent_steps":86,"n_tasks_passed_any":90,"median_input_tokens":8037064.5,"median_output_tokens":66088,"mean_duration_seconds":897.5133296747788,"median_duration_seconds":688.5861825,"median_peak_context_tokens":154817.5,"median_output_tokens_to_pass":61398}},"release_date":"2026-07-09"},"id":"empiriolabs/muse-spark-1-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":2.361142644469026,"intelligence":0.5331858407079646,"latency":897.5133296747788,"speed":82.45941080429397,"context":154817.5,"passAt4":0.7964601769911505}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/muse-spark-1-2","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5699155383909527,"ci_lo":0.5274295943524101,"model":"muse-spark-1-2","config":"mini_swe_agent_muse_spark_1_2_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02124297201927127,"harness":"mini-swe-agent","version":"v1.1","n_passed":248,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":248,"pass_at_1":0.5486725663716814,"pass_at_4":0.8141592920353983,"pass_rate":0.5486725663716814,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.6955048180309733,"n_tasks_in_set":113,"median_cost_usd":2.6840506,"mean_agent_steps":100.75884955752213,"reasoning_effort":"xhigh","mean_cache_tokens":12584988.949115044,"mean_input_tokens":13693824.435840707,"n_tasks_attempted":113,"mean_output_tokens":99226.38053097345,"median_agent_steps":94,"n_tasks_passed_any":92,"median_input_tokens":10339991,"median_output_tokens":81250,"mean_duration_seconds":927.8692516349557,"median_duration_seconds":784.787489,"median_peak_context_tokens":189481,"median_output_tokens_to_pass":77863}},"release_date":"2026-08-05"},"id":"empiriolabs/muse-spark-1-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":3.6955048180309733,"intelligence":0.5486725663716814,"latency":927.8692516349557,"speed":106.94004608529833,"context":189481,"passAt4":0.8141592920353983}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/muse-spark-1-3","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-02"},"id":"empiriolabs/muse-spark-1-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/nova-lite-1-0","base_model_name":"","max_context_window":300000,"input_cost":0.069,"output_cost":0.28,"cache_hit_input_cost":0.0386,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-03"},"id":"empiriolabs/nova-lite-1-0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/nova-lite-2","base_model_name":"","max_context_window":1000000,"input_cost":0.38,"output_cost":3.16,"cache_hit_input_cost":0.2128,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"empiriolabs/nova-lite-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/nova-micro-1-0","base_model_name":"","max_context_window":128000,"input_cost":0.04,"output_cost":0.16,"cache_hit_input_cost":0.0224,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-03"},"id":"empiriolabs/nova-micro-1-0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.1285,"average_ttft":null,"average_latency":0.7267,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.1285,"average_ttft":null,"average_latency":0.7267,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/nova-pro-1-0","base_model_name":"","max_context_window":300000,"input_cost":2.4,"output_cost":9.6,"cache_hit_input_cost":2.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-03"},"id":"empiriolabs/nova-pro-1-0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-122b-a10b","base_model_name":"","max_context_window":256000,"input_cost":0.115,"output_cost":0.917,"cache_hit_input_cost":0.115,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-24"},"id":"empiriolabs/qwen3-5-122b-a10b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-27b","base_model_name":"","max_context_window":256000,"input_cost":0.086,"output_cost":0.688,"cache_hit_input_cost":0.086,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-24"},"id":"empiriolabs/qwen3-5-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-35b-a3b","base_model_name":"","max_context_window":256000,"input_cost":0.057,"output_cost":0.459,"cache_hit_input_cost":0.057,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-24"},"id":"empiriolabs/qwen3-5-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-397b-a17b","base_model_name":"","max_context_window":256000,"input_cost":0.172,"output_cost":1.032,"cache_hit_input_cost":0.172,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-16"},"id":"empiriolabs/qwen3-5-397b-a17b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-4b","base_model_name":"empiriolabs/qwen3-5-4b","max_context_window":262144,"input_cost":0.04,"output_cost":0.07,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-02","is_available_on_credits":true},"id":"empiriolabs/qwen3-5-4b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.0768,"average_ttft":null,"average_latency":1.0057,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.0768,"average_ttft":null,"average_latency":1.0057,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-9b","base_model_name":"empiriolabs/qwen3-5-9b","max_context_window":262144,"input_cost":0.09,"output_cost":0.13,"cache_hit_input_cost":0.045,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-23","is_available_on_credits":true},"id":"empiriolabs/qwen3-5-9b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.7602,"average_ttft":null,"average_latency":1.0587,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.7602,"average_ttft":null,"average_latency":1.0587,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.09,"output_cost":0.368,"cache_hit_input_cost":0.09,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-24"},"id":"empiriolabs/qwen3-5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-omni-flash","base_model_name":"","max_context_window":256000,"input_cost":0.8,"output_cost":4.4,"cache_hit_input_cost":0.8,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-30"},"id":"empiriolabs/qwen3-5-omni-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-omni-plus","base_model_name":"","max_context_window":256000,"input_cost":2.8,"output_cost":16.6,"cache_hit_input_cost":2.8,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-30"},"id":"empiriolabs/qwen3-5-omni-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-5-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.36,"output_cost":2.21,"cache_hit_input_cost":0.36,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-16"},"id":"empiriolabs/qwen3-5-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-6-27b","base_model_name":"","max_context_window":256000,"input_cost":0.412564,"output_cost":2.475384,"cache_hit_input_cost":0.412564,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"empiriolabs/qwen3-6-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-6-35b-a3b","base_model_name":"empiriolabs/qwen3-6-35b-a3b","max_context_window":131072,"input_cost":0.07,"output_cost":0.42,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16","is_available_on_credits":true},"id":"empiriolabs/qwen3-6-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":72.5975,"average_ttft":null,"average_latency":1.5746,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":72.5975,"average_ttft":null,"average_latency":1.5746,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-6-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"empiriolabs/qwen3-6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-6-max-preview","base_model_name":"","max_context_window":256000,"input_cost":1.31,"output_cost":7.88,"cache_hit_input_cost":1.31,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-20"},"id":"empiriolabs/qwen3-6-max-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-6-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"empiriolabs/qwen3-6-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-7-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.03,"output_cost":0.13,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-15"},"id":"empiriolabs/qwen3-7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":48.3505,"average_ttft":null,"average_latency":2.5232,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.3505,"average_ttft":null,"average_latency":2.5232,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-7-max","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":7.5,"cache_hit_input_cost":2.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-21"},"id":"empiriolabs/qwen3-7-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-7-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-01"},"id":"empiriolabs/qwen3-7-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-8-27b","base_model_name":"","max_context_window":262144,"input_cost":0.17,"output_cost":0.5,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-14"},"id":"empiriolabs/qwen3-8-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-8-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.16,"output_cost":0.47,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-26"},"id":"empiriolabs/qwen3-8-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-8-max","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-08-03"},"id":"empiriolabs/qwen3-8-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":3.7290646500445437,"intelligence":0.5746102449888641,"latency":2567.2746634654786,"speed":37.03350637976676,"context":160572,"passAt4":0.831858407079646}},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-8-max-0902","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-09-02"},"id":"empiriolabs/qwen3-8-max-0902","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-8-omni-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.3,"output_cost":0.94,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-17"},"id":"empiriolabs/qwen3-8-omni-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-max","base_model_name":"","max_context_window":256000,"input_cost":1.08,"output_cost":5.52,"cache_hit_input_cost":1.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-23"},"id":"empiriolabs/qwen3-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-max-preview","base_model_name":"","max_context_window":256000,"input_cost":1.08,"output_cost":4.8,"cache_hit_input_cost":1.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-05"},"id":"empiriolabs/qwen3-max-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/qwen3-max-thinking","base_model_name":"","max_context_window":256000,"input_cost":1.08,"output_cost":5.52,"cache_hit_input_cost":1.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-23"},"id":"empiriolabs/qwen3-max-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/seed-2-0-code","base_model_name":"","max_context_window":256000,"input_cost":0.4,"output_cost":2.4,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-14"},"id":"empiriolabs/seed-2-0-code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/seed-2-0-lite","base_model_name":"","max_context_window":256000,"input_cost":0.31,"output_cost":2.5,"cache_hit_input_cost":0.31,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-14"},"id":"empiriolabs/seed-2-0-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/seed-2-0-mini","base_model_name":"","max_context_window":256000,"input_cost":0.12,"output_cost":0.5,"cache_hit_input_cost":0.12,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-14"},"id":"empiriolabs/seed-2-0-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/seed-2-0-pro","base_model_name":"","max_context_window":256000,"input_cost":0.63,"output_cost":3.79,"cache_hit_input_cost":0.63,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-14"},"id":"empiriolabs/seed-2-0-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/seed-2-1-turbo","base_model_name":"","max_context_window":256000,"input_cost":0.63,"output_cost":3.13,"cache_hit_input_cost":0.63,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-13"},"id":"empiriolabs/seed-2-1-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/step-3-5-flash","base_model_name":"","max_context_window":256000,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-12"},"id":"empiriolabs/step-3-5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/step-3-5-flash-2603","base_model_name":"","max_context_window":256000,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"empiriolabs/step-3-5-flash-2603","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/step-3-7-flash","base_model_name":"","max_context_window":256000,"input_cost":0.2,"output_cost":1.15,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-28"},"id":"empiriolabs/step-3-7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/step-5-preview","base_model_name":"","max_context_window":1024000,"input_cost":1,"output_cost":2.7,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-15"},"id":"empiriolabs/step-5-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/stepaudio-2-5-chat","base_model_name":"","max_context_window":256000,"input_cost":1.5,"output_cost":3.5,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"empiriolabs/stepaudio-2-5-chat","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"EmpirioLabs","provider_id":"empiriolabs","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376993Z","updated_at":"2026-07-23T06:47:03.376997Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.empiriolabs.ai/v1/models"},"kind":"host","id":"empiriolabs"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"empiriolabs/stepaudio-3-chat","base_model_name":"","max_context_window":262144,"input_cost":1.5,"output_cost":3.5,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-09"},"id":"empiriolabs/stepaudio-3-chat","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/darkc0de/XortronCriminalComputingConfig","base_model_name":"darkc0de/XortronCriminalComputingConfig","max_context_window":32768,"input_cost":0.7,"output_cost":1.16,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-23"},"id":"featherless_ai/darkc0de/XortronCriminalComputingConfig","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.9702,"average_ttft":null,"average_latency":14.4383,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.9702,"average_ttft":null,"average_latency":14.4383,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","base_model_name":"deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","max_context_window":32768,"input_cost":0.4312,"output_cost":1.12,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-24"},"id":"featherless_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":38.9388,"average_ttft":null,"average_latency":7.6455,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.9388,"average_ttft":null,"average_latency":7.6455,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-V3-0324","base_model_name":"deepseek-ai/DeepSeek-V3-0324","max_context_window":131072,"input_cost":0.385,"output_cost":1.625,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek-ai/DeepSeek-V3-0324"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-25"},"id":"featherless_ai/deepseek-ai/DeepSeek-V3-0324","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.3553,"average_ttft":null,"average_latency":0.8521,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.3553,"average_ttft":null,"average_latency":0.8521,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-V3.1","base_model_name":"deepseek-ai/DeepSeek-V3.1","max_context_window":131072,"input_cost":0.285,"output_cost":1,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"featherless_ai/deepseek-ai/DeepSeek-V3.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.6454,"average_ttft":null,"average_latency":3.0644,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.6454,"average_ttft":null,"average_latency":3.0644,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-V3.2","base_model_name":"deepseek-ai/DeepSeek-V3.2","max_context_window":131072,"input_cost":0.264,"output_cost":0.41,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-01-26"},"id":"featherless_ai/deepseek-ai/DeepSeek-V3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.7846,"average_ttft":null,"average_latency":2.3429,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.7846,"average_ttft":null,"average_latency":2.3429,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"deepseek-ai/DeepSeek-V4-Flash","max_context_window":262144,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-28"},"id":"featherless_ai/deepseek-ai/DeepSeek-V4-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":14.9116,"average_ttft":null,"average_latency":0.6603,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.9116,"average_ttft":null,"average_latency":0.6603,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"deepseek-ai/DeepSeek-V4-Pro","max_context_window":262144,"input_cost":1.6,"output_cost":3.2,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-28"},"id":"featherless_ai/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.6701,"average_ttft":null,"average_latency":3.955,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.6701,"average_ttft":null,"average_latency":3.955,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Doctor-Shotgun/L3.3-70B-Magnum-Diamond","base_model_name":"Doctor-Shotgun/L3.3-70B-Magnum-Diamond","max_context_window":32768,"input_cost":2.6,"output_cost":3,"cache_hit_input_cost":4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-01"},"id":"featherless_ai/Doctor-Shotgun/L3.3-70B-Magnum-Diamond","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.2936,"average_ttft":null,"average_latency":6.7605,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.2936,"average_ttft":null,"average_latency":6.7605,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/dphn/Dolphin-Mistral-24B-Venice-Edition","base_model_name":"dphn/Dolphin-Mistral-24B-Venice-Edition","max_context_window":32768,"input_cost":0.7,"output_cost":1.16,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-25"},"id":"featherless_ai/dphn/Dolphin-Mistral-24B-Venice-Edition","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.6878,"average_ttft":null,"average_latency":7.8031,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.6878,"average_ttft":null,"average_latency":7.8031,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-2-9b-it","base_model_name":"google/gemma-2-9b-it","max_context_window":16384,"input_cost":0.4312,"output_cost":1.12,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-28"},"id":"featherless_ai/google/gemma-2-9b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.9838,"average_ttft":null,"average_latency":4.5421,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.9838,"average_ttft":null,"average_latency":4.5421,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-3-12b-it","base_model_name":"google/gemma-3-12b-it","max_context_window":32768,"input_cost":0.05,"output_cost":0.15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"featherless_ai/google/gemma-3-12b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.4632,"average_ttft":null,"average_latency":2.7893,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.4632,"average_ttft":null,"average_latency":2.7893,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-4-26B-A4B-it","base_model_name":"google/gemma-4-26B-A4B-it","max_context_window":32768,"input_cost":0.07,"output_cost":0.34,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-08"},"id":"featherless_ai/google/gemma-4-26B-A4B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.0812,"average_ttft":1.7162,"average_latency":4.3767,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.0812,"average_ttft":1.7162,"average_latency":4.3767,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-4-31B-it","base_model_name":"google/gemma-4-31B-it","max_context_window":32768,"input_cost":0.12,"output_cost":0.36,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-08"},"id":"featherless_ai/google/gemma-4-31B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.2664,"average_ttft":null,"average_latency":5.2259,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.2664,"average_ttft":null,"average_latency":5.2259,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-4-E4B-it","base_model_name":"google/gemma-4-E4B-it","max_context_window":32768,"input_cost":0.1,"output_cost":0.2,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-08"},"id":"featherless_ai/google/gemma-4-E4B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.623,"average_ttft":null,"average_latency":1.2285,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.623,"average_ttft":null,"average_latency":1.2285,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/google/gemma-7b-it","base_model_name":"google/gemma-7b-it","max_context_window":8192,"input_cost":0.4312,"output_cost":1.12,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-24"},"id":"featherless_ai/google/gemma-7b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.326,"average_ttft":null,"average_latency":7.6524,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.326,"average_ttft":null,"average_latency":7.6524,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","base_model_name":"huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","max_context_window":32768,"input_cost":2.88,"output_cost":2.88,"cache_hit_input_cost":4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-30"},"id":"featherless_ai/huihui-ai/DeepSeek-R1-Distill-Llama-70B-abliterated","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.8986,"average_ttft":null,"average_latency":7.3088,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.8986,"average_ttft":null,"average_latency":7.3088,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/huihui-ai/Llama-3.3-70B-Instruct-abliterated","base_model_name":"huihui-ai/Llama-3.3-70B-Instruct-abliterated","max_context_window":32768,"input_cost":0.65,"output_cost":0.75,"cache_hit_input_cost":4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-16"},"id":"featherless_ai/huihui-ai/Llama-3.3-70B-Instruct-abliterated","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.5961,"average_ttft":null,"average_latency":0.9979,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.5961,"average_ttft":null,"average_latency":0.9979,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/huihui-ai/Qwen2.5-72B-Instruct-abliterated","base_model_name":"huihui-ai/Qwen2.5-72B-Instruct-abliterated","max_context_window":32768,"input_cost":1.48,"output_cost":1.6,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-07"},"id":"featherless_ai/huihui-ai/Qwen2.5-72B-Instruct-abliterated","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.8314,"average_ttft":null,"average_latency":7.7984,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.8314,"average_ttft":null,"average_latency":7.7984,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/LyraNovaHeart/Stellar-Odyssey-12b-v0.0","base_model_name":"LyraNovaHeart/Stellar-Odyssey-12b-v0.0","max_context_window":32768,"input_cost":0.2175,"output_cost":0.2475,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-26"},"id":"featherless_ai/LyraNovaHeart/Stellar-Odyssey-12b-v0.0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":19.5415,"average_ttft":null,"average_latency":1.7826,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.5415,"average_ttft":null,"average_latency":1.7826,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/MarinaraSpaghetti/NemoMix-Unleashed-12B","base_model_name":"MarinaraSpaghetti/NemoMix-Unleashed-12B","max_context_window":32768,"input_cost":0.87,"output_cost":0.99,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-11"},"id":"featherless_ai/MarinaraSpaghetti/NemoMix-Unleashed-12B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.5426,"average_ttft":null,"average_latency":5.8133,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.5426,"average_ttft":null,"average_latency":5.8133,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/MiniMaxAI/MiniMax-M2.5","base_model_name":"MiniMaxAI/MiniMax-M2.5","max_context_window":204800,"input_cost":0.295,"output_cost":1.2,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"featherless_ai/MiniMaxAI/MiniMax-M2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.3935,"average_ttft":null,"average_latency":3.6363,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.3935,"average_ttft":null,"average_latency":3.6363,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/mistralai/Mistral-7B-Instruct-v0.2","base_model_name":"mistralai/Mistral-7B-Instruct-v0.2","max_context_window":8192,"input_cost":0.1,"output_cost":0.2,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-25"},"id":"featherless_ai/mistralai/Mistral-7B-Instruct-v0.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":19.1732,"average_ttft":null,"average_latency":2.4574,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.1732,"average_ttft":null,"average_latency":2.4574,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/mistralai/Mistral-Nemo-Instruct-2407","base_model_name":"mistralai/Mistral-Nemo-Instruct-2407","max_context_window":32768,"input_cost":0.2175,"output_cost":0.2475,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["mistralai/Mistral-Nemo-Instruct-2407"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-03"},"id":"featherless_ai/mistralai/Mistral-Nemo-Instruct-2407","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.6894,"average_ttft":null,"average_latency":2.9939,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.6894,"average_ttft":null,"average_latency":2.9939,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated","base_model_name":"mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated","max_context_window":32768,"input_cost":0.05,"output_cost":0.08,"cache_hit_input_cost":0.8,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-27"},"id":"featherless_ai/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.5587,"average_ttft":null,"average_latency":2.719,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.5587,"average_ttft":null,"average_latency":2.719,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/moonshotai/Kimi-K2-Instruct","base_model_name":"moonshotai/Kimi-K2-Instruct","max_context_window":32768,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-14"},"id":"featherless_ai/moonshotai/Kimi-K2-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.3267,"average_ttft":null,"average_latency":3.3803,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.3267,"average_ttft":null,"average_latency":3.3803,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/moonshotai/Kimi-K2-Instruct-0905","base_model_name":"moonshotai/Kimi-K2-Instruct-0905","max_context_window":32768,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-10"},"id":"featherless_ai/moonshotai/Kimi-K2-Instruct-0905","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.0905,"average_ttft":null,"average_latency":2.6279,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.0905,"average_ttft":null,"average_latency":2.6279,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/moonshotai/Kimi-K2.5","base_model_name":"moonshotai/Kimi-K2.5","max_context_window":262144,"input_cost":0.8,"output_cost":3.4,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-27"},"id":"featherless_ai/moonshotai/Kimi-K2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.7917,"average_ttft":null,"average_latency":9.1343,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.7917,"average_ttft":null,"average_latency":9.1343,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/moonshotai/Kimi-K2.6","base_model_name":"moonshotai/Kimi-K2.6","max_context_window":262144,"input_cost":0.8,"output_cost":3.4,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-23"},"id":"featherless_ai/moonshotai/Kimi-K2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.1867,"average_ttft":null,"average_latency":8.1539,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.1867,"average_ttft":null,"average_latency":8.1539,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/NeverSleep/Llama-3-Lumimaid-70B-v0.1","base_model_name":"NeverSleep/Llama-3-Lumimaid-70B-v0.1","max_context_window":8192,"input_cost":3.5,"output_cost":8.3,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-06-21"},"id":"featherless_ai/NeverSleep/Llama-3-Lumimaid-70B-v0.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.5994,"average_ttft":null,"average_latency":12.179,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.5994,"average_ttft":null,"average_latency":12.179,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-07"},"id":"featherless_ai/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":61.6866,"average_ttft":null,"average_latency":1.0599,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":61.6866,"average_ttft":null,"average_latency":1.0599,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.04,"output_cost":0.15,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-02"},"id":"featherless_ai/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.603,"average_ttft":null,"average_latency":6.5012,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.603,"average_ttft":null,"average_latency":6.5012,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen2.5-1.5B-Instruct","base_model_name":"Qwen/Qwen2.5-1.5B-Instruct","max_context_window":32768,"input_cost":0.04,"output_cost":0.08,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-12"},"id":"featherless_ai/Qwen/Qwen2.5-1.5B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.413,"average_ttft":null,"average_latency":8.2037,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.413,"average_ttft":null,"average_latency":8.2037,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen2.5-14B-Instruct","base_model_name":"Qwen/Qwen2.5-14B-Instruct","max_context_window":32768,"input_cost":0.1078,"output_cost":0.28,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-02-11"},"id":"featherless_ai/Qwen/Qwen2.5-14B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.837,"average_ttft":null,"average_latency":1.3077,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.837,"average_ttft":null,"average_latency":1.3077,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen2.5-32B-Instruct","base_model_name":"Qwen/Qwen2.5-32B-Instruct","max_context_window":32768,"input_cost":0.68,"output_cost":1.2,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Qwen/Qwen2.5-32B-Instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-20"},"id":"featherless_ai/Qwen/Qwen2.5-32B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":2.3431,"average_ttft":null,"average_latency":3.4415,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.3431,"average_ttft":null,"average_latency":3.4415,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen2.5-72B-Instruct","base_model_name":"Qwen/Qwen2.5-72B-Instruct","max_context_window":32768,"input_cost":0.37,"output_cost":0.4,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Qwen/Qwen2.5-72B-Instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-18"},"id":"featherless_ai/Qwen/Qwen2.5-72B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.5742,"average_ttft":null,"average_latency":4.2028,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.5742,"average_ttft":null,"average_latency":4.2028,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-14B","base_model_name":"Qwen/Qwen3-14B","max_context_window":32768,"input_cost":0.12,"output_cost":0.24,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Qwen/Qwen3-14B"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-05-13"},"id":"featherless_ai/Qwen/Qwen3-14B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.9107,"average_ttft":null,"average_latency":7.0676,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.9107,"average_ttft":null,"average_latency":7.0676,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-8B","base_model_name":"Qwen/Qwen3-8B","max_context_window":32768,"input_cost":0.117,"output_cost":0.455,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-05-13"},"id":"featherless_ai/Qwen/Qwen3-8B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.9221,"average_ttft":null,"average_latency":6.0282,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.9221,"average_ttft":null,"average_latency":6.0282,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-Coder-Next","base_model_name":"Qwen/Qwen3-Coder-Next","max_context_window":32768,"input_cost":0.16,"output_cost":1.15,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"featherless_ai/Qwen/Qwen3-Coder-Next","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.0598,"average_ttft":null,"average_latency":1.433,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.0598,"average_ttft":null,"average_latency":1.433,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-Embedding-0.6B","base_model_name":"Qwen/Qwen3-Embedding-0.6B","max_context_window":32768,"input_cost":0.01,"output_cost":0.02,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"featherless_ai/Qwen/Qwen3-Embedding-0.6B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-Embedding-4B","base_model_name":"Qwen/Qwen3-Embedding-4B","max_context_window":32768,"input_cost":0.02,"output_cost":0,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"featherless_ai/Qwen/Qwen3-Embedding-4B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3-Embedding-8B","base_model_name":"Qwen/Qwen3-Embedding-8B","max_context_window":32768,"input_cost":0.01,"output_cost":0,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"featherless_ai/Qwen/Qwen3-Embedding-8B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3.5-27B","base_model_name":"Qwen/Qwen3.5-27B","max_context_window":32768,"input_cost":0.3,"output_cost":2.4,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-16"},"id":"featherless_ai/Qwen/Qwen3.5-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.1398,"average_ttft":null,"average_latency":12.3543,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.1398,"average_ttft":null,"average_latency":12.3543,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3.5-9B","base_model_name":"Qwen/Qwen3.5-9B","max_context_window":32768,"input_cost":0.17,"output_cost":0.25,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-08"},"id":"featherless_ai/Qwen/Qwen3.5-9B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":33.3071,"average_ttft":null,"average_latency":4.2403,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":33.3071,"average_ttft":null,"average_latency":4.2403,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Qwen/Qwen3.6-35B-A3B","base_model_name":"Qwen/Qwen3.6-35B-A3B","max_context_window":32768,"input_cost":0.186,"output_cost":1.1138,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-28"},"id":"featherless_ai/Qwen/Qwen3.6-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.6594,"average_ttft":null,"average_latency":7.8766,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.6594,"average_ttft":null,"average_latency":7.8766,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Sao10K/L3-8B-Stheno-v3.2","base_model_name":"Sao10K/L3-8B-Stheno-v3.2","max_context_window":8192,"input_cost":0.37,"output_cost":0.38,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Sao10K/L3-8B-Stheno-v3.2"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-17"},"id":"featherless_ai/Sao10K/L3-8B-Stheno-v3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.3098,"average_ttft":null,"average_latency":1.4394,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.3098,"average_ttft":null,"average_latency":1.4394,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/Sao10K/Llama-3.1-8B-Stheno-v3.4","base_model_name":"Sao10K/Llama-3.1-8B-Stheno-v3.4","max_context_window":32768,"input_cost":0.2,"output_cost":0.32,"cache_hit_input_cost":0.8,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-03"},"id":"featherless_ai/Sao10K/Llama-3.1-8B-Stheno-v3.4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.3585,"average_ttft":null,"average_latency":1.35,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.3585,"average_ttft":null,"average_latency":1.35,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/TheDrummer/Anubis-70B-v1.2","base_model_name":"TheDrummer/Anubis-70B-v1.2","max_context_window":32768,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-28"},"id":"featherless_ai/TheDrummer/Anubis-70B-v1.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.2514,"average_ttft":null,"average_latency":8.603,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.2514,"average_ttft":null,"average_latency":8.603,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/TheDrummer/Cydonia-24B-v4.3","base_model_name":"TheDrummer/Cydonia-24B-v4.3","max_context_window":32768,"input_cost":0.7,"output_cost":1.16,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-09"},"id":"featherless_ai/TheDrummer/Cydonia-24B-v4.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.4521,"average_ttft":null,"average_latency":3.0079,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.4521,"average_ttft":null,"average_latency":3.0079,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/ToxicityPrompts/PolyGuard-Qwen","base_model_name":"ToxicityPrompts/PolyGuard-Qwen","max_context_window":32768,"input_cost":0.4,"output_cost":0.8,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-05"},"id":"featherless_ai/ToxicityPrompts/PolyGuard-Qwen","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.1789,"average_ttft":null,"average_latency":6.4577,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.1789,"average_ttft":null,"average_latency":6.4577,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/XiaomiMiMo/MiMo-V2-Flash","base_model_name":"XiaomiMiMo/MiMo-V2-Flash","max_context_window":262144,"input_cost":0.1078,"output_cost":0.28,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-11"},"id":"featherless_ai/XiaomiMiMo/MiMo-V2-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/zai-org/GLM-4.6","base_model_name":"zai-org/GLM-4.6","max_context_window":202752,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-01"},"id":"featherless_ai/zai-org/GLM-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.3117,"average_ttft":null,"average_latency":16.5573,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.3117,"average_ttft":null,"average_latency":16.5573,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/zai-org/GLM-4.7","base_model_name":"zai-org/GLM-4.7","max_context_window":202752,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-31"},"id":"featherless_ai/zai-org/GLM-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.4115,"average_ttft":null,"average_latency":8.3992,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.4115,"average_ttft":null,"average_latency":8.3992,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/zai-org/GLM-5","base_model_name":"zai-org/GLM-5","max_context_window":202752,"input_cost":0.95,"output_cost":3.15,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"featherless_ai/zai-org/GLM-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":14.6519,"average_ttft":null,"average_latency":4.3526,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.6519,"average_ttft":null,"average_latency":4.3526,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/zai-org/GLM-5.1","base_model_name":"zai-org/GLM-5.1","max_context_window":202752,"input_cost":1.3,"output_cost":4.3,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-08"},"id":"featherless_ai/zai-org/GLM-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.4483,"average_ttft":null,"average_latency":2.6347,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.4483,"average_ttft":null,"average_latency":2.6347,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Featherless","provider_id":"featherless","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175549Z","updated_at":"2026-06-09T21:22:10.715436Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.featherless.ai/v1/models"},"kind":"host","id":"featherless"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"featherless_ai/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":262144,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16"},"id":"featherless_ai/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.1034,"average_ttft":null,"average_latency":6.5723,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.1034,"average_ttft":null,"average_latency":6.5723,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/deepseek-v4p1-flash","base_model_name":"fireworks_ai/deepseek-v4p1-flash","max_context_window":1048576,"input_cost":0.22,"output_cost":0.66,"cache_hit_input_cost":0.007,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10","is_available_on_credits":false},"id":"fireworks_ai/deepseek-v4p1-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/ember-1","base_model_name":"fireworks_ai/ember-1","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"release_date":"2026-09-22","is_available_on_credits":false},"id":"fireworks_ai/ember-1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/glm-5p2","base_model_name":"fireworks_ai/glm-5p2","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16","is_available_on_credits":false},"id":"fireworks_ai/glm-5p2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/glm-5p3","base_model_name":"fireworks_ai/glm-5p3","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-28","is_available_on_credits":false},"id":"fireworks_ai/glm-5p3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/glm-5p3-flash","base_model_name":"fireworks_ai/glm-5p3-flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26","is_available_on_credits":false},"id":"fireworks_ai/glm-5p3-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/gpt-oss-120b","base_model_name":"fireworks_ai/gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["fireworks_ai/gpt-oss-120b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"fireworks_ai/gpt-oss-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/inkling","base_model_name":"fireworks_ai/inkling","max_context_window":1048576,"input_cost":1,"output_cost":4.05,"cache_hit_input_cost":0.17,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-14","is_available_on_credits":false},"id":"fireworks_ai/inkling","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/kimi-k3","base_model_name":"fireworks_ai/kimi-k3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-19","is_available_on_credits":false},"id":"fireworks_ai/kimi-k3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":4.654682129933482,"intelligence":0.6851441241685144,"latency":4541.447376412417,"speed":17.94578596140072,"context":130945,"passAt4":0.8938053097345132}},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/minimax-m3","base_model_name":"fireworks_ai/minimax-m3","max_context_window":512000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-11","is_available_on_credits":false},"id":"fireworks_ai/minimax-m3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/nemotron-3-ultra-nvfp4","base_model_name":"fireworks_ai/nemotron-3-ultra-nvfp4","max_context_window":262144,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.12,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-02","is_available_on_credits":false},"id":"fireworks_ai/nemotron-3-ultra-nvfp4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/nemotron-lightning-3p5-30b-a3b","base_model_name":"fireworks_ai/nemotron-lightning-3p5-30b-a3b","max_context_window":262144,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-07","is_available_on_credits":false},"id":"fireworks_ai/nemotron-lightning-3p5-30b-a3b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/qwen3p8-2p4t-a95b","base_model_name":"fireworks_ai/qwen3p8-2p4t-a95b","max_context_window":262144,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-12","is_available_on_credits":false},"id":"fireworks_ai/qwen3p8-2p4t-a95b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Fireworks","provider_id":"fireworks","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.925664Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.fireworks.ai/v1/accounts/fireworks/models"},"kind":"host","id":"fireworks"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"fireworks_ai/qwen3p8-max","base_model_name":"fireworks_ai/qwen3p8-max","max_context_window":1048576,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-08-05","is_available_on_credits":false},"id":"fireworks_ai/qwen3p8-max","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"friendliai/deepseek-ai/DeepSeek-V3.2","base_model_name":"deepseek-ai/DeepSeek-V3.2","max_context_window":163840,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-03-07"},"id":"friendliai/deepseek-ai/DeepSeek-V3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.0465,"average_ttft":null,"average_latency":1.1959,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.0465,"average_ttft":null,"average_latency":1.1959,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"friendliai/google/gemma-4-31B-it","base_model_name":"google/gemma-4-31B-it","max_context_window":262144,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.14,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-01"},"id":"friendliai/google/gemma-4-31B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.331,"average_ttft":null,"average_latency":0.4117,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.331,"average_ttft":null,"average_latency":0.4117,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"friendliai/MiniMaxAI/MiniMax-M2.5","base_model_name":"MiniMaxAI/MiniMax-M2.5","max_context_window":196608,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-19"},"id":"friendliai/MiniMaxAI/MiniMax-M2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":142.6059,"average_ttft":null,"average_latency":0.7691,"uptime_percent":100,"cache_hit_percentage":50},"throughput":{"average_tps":142.6059,"average_ttft":null,"average_latency":0.7691,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"friendliai/zai-org/GLM-5.1","base_model_name":"zai-org/GLM-5.1","max_context_window":202752,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"friendliai/zai-org/GLM-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":64.5731,"average_ttft":null,"average_latency":1.5092,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":64.5731,"average_ttft":null,"average_latency":1.5092,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"friendliai/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16"},"id":"friendliai/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":96.7468,"average_ttft":null,"average_latency":0.639,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":96.7468,"average_ttft":null,"average_latency":0.639,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"friendliai/zai-org/GLM-5.3","base_model_name":"","max_context_window":1048576,"input_cost":1.26,"output_cost":3.96,"cache_hit_input_cost":0.234,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-28"},"id":"friendliai/zai-org/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"FriendliAI","provider_id":"friendliai","extra_kwargs":{},"created_at":"2026-06-08T03:52:41.705779Z","updated_at":"2026-06-08T03:52:41.705807Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.friendli.ai/serverless/v1/models"},"kind":"host","id":"friendliai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"friendliai/zai-org/GLM-5.3-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-28"},"id":"friendliai/zai-org/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":85.396,"average_ttft":null,"average_latency":0.6441,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":85.396,"average_ttft":null,"average_latency":0.6441,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"gemini/gemini-2.5-computer-use-preview-10-2025","base_model_name":"gemini-2.5-computer-use-preview-10-2025","max_context_window":131072,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-07"},"id":"gemini/gemini-2.5-computer-use-preview-10-2025","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":66.6667,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-2.5-flash","base_model_name":"gemini/gemini-2.5-flash","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gemini/gemini-2.5-flash"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2025-04-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-2.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":186.9381,"average_ttft":null,"average_latency":18.1628,"uptime_percent":100,"cache_hit_percentage":1.5701},"throughput":{"average_tps":186.9381,"average_ttft":null,"average_latency":18.1628,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-2.5-flash-lite","base_model_name":"gemini/gemini-2.5-flash-lite","max_context_window":1048576,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gemini/gemini-2.5-flash-lite"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-06-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-2.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":186.1006,"average_ttft":null,"average_latency":2.0024,"uptime_percent":99.9186,"cache_hit_percentage":0.2709},"throughput":{"average_tps":186.1006,"average_ttft":null,"average_latency":2.0024,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-2.5-pro","base_model_name":"gemini/gemini-2.5-pro","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gemini/gemini-2.5-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-03-25","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":101.6051,"average_ttft":null,"average_latency":6.1384,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":101.6051,"average_ttft":null,"average_latency":6.1384,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3-flash-preview","base_model_name":"gemini/gemini-3-flash-preview","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gemini/gemini-3-flash-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-12-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3-flash-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":118.6866,"average_ttft":3.6342,"average_latency":7.5042,"uptime_percent":99.2938,"cache_hit_percentage":0.2257},"throughput":{"average_tps":118.6866,"average_ttft":3.6342,"average_latency":7.5042,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.1-flash-lite","base_model_name":"gemini/gemini-3.1-flash-lite","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.1-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":246.2441,"average_ttft":0.967,"average_latency":3.6161,"uptime_percent":99.7497,"cache_hit_percentage":0.0863},"throughput":{"average_tps":246.2441,"average_ttft":0.967,"average_latency":3.6161,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.1-flash-lite-preview","base_model_name":"gemini/gemini-3.1-flash-lite-preview","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.1-flash-lite-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":139.8881,"average_ttft":null,"average_latency":1.1459,"uptime_percent":100,"cache_hit_percentage":2.1992},"throughput":{"average_tps":139.8881,"average_ttft":null,"average_latency":1.1459,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.1-pro-preview","base_model_name":"gemini/gemini-3.1-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2026-02-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.1-pro-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":393.5899,"average_ttft":15.3096,"average_latency":14.049,"uptime_percent":99.5546,"cache_hit_percentage":0},"throughput":{"average_tps":393.5899,"average_ttft":15.3096,"average_latency":14.049,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"gemini/gemini-3.1-pro-preview-customtools","base_model_name":"gemini-3.1-pro-preview-customtools","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"release_date":"2026-02-25"},"id":"gemini/gemini-3.1-pro-preview-customtools","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.4464,"average_ttft":null,"average_latency":1.999,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.4464,"average_ttft":null,"average_latency":1.999,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.5-flash","base_model_name":"gemini/gemini-3.5-flash","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2026-05-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11717.2057,"average_ttft":3.5204,"average_latency":3.0971,"uptime_percent":99.5485,"cache_hit_percentage":79.833},"throughput":{"average_tps":11717.2057,"average_ttft":3.5204,"average_latency":3.0971,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.5-flash-lite","base_model_name":"gemini/gemini-3.5-flash-lite","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-07-21","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":70.3847,"average_ttft":null,"average_latency":1.889,"uptime_percent":91.2698,"cache_hit_percentage":25.5928},"throughput":{"average_tps":70.3847,"average_ttft":null,"average_latency":1.889,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.6-flash","base_model_name":"gemini/gemini-3.6-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5038626982845081,"ci_lo":0.4297656202995626,"model":"gemini-3-6-flash","config":"mini_swe_agent_gemini_3_6_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.037048538992472776,"harness":"mini-swe-agent","version":"v1.1","n_passed":211,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":211,"pass_at_1":0.4668141592920354,"pass_at_4":0.7522123893805309,"pass_rate":0.4668141592920354,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.419013277333334,"n_tasks_in_set":113,"median_cost_usd":3.444695325000001,"mean_agent_steps":116.73333333333333,"reasoning_effort":"high","mean_cache_tokens":11254636.448888889,"mean_input_tokens":12595957.344444444,"n_tasks_attempted":113,"mean_output_tokens":95844.86222222222,"median_agent_steps":108,"n_tasks_passed_any":85,"median_input_tokens":8949018.5,"median_output_tokens":86727,"mean_duration_seconds":1477.8607510707964,"median_duration_seconds":1214.8670550000002,"median_peak_context_tokens":151398.5,"median_output_tokens_to_pass":83414}},"context_size":1048576,"release_date":"2026-07-21","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1175.3308,"average_ttft":1.026,"average_latency":13.246,"uptime_percent":33.3481,"cache_hit_percentage":1.1157},"throughput":{"average_tps":1175.3308,"average_ttft":1.026,"average_latency":13.246,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.7-flash","base_model_name":"gemini-3.7-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}},"context_size":1048576,"release_date":"2026-08-13","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"gemini/gemini-3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":136.2944,"average_ttft":null,"average_latency":3.4098,"uptime_percent":99.8046,"cache_hit_percentage":0.1257},"throughput":{"average_tps":136.2944,"average_ttft":null,"average_latency":3.4098,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemini-3.8-flash","base_model_name":"gemini/gemini-3.8-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":0.2,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7524281656234058,"ci_lo":0.7240819014906883,"model":"gemini-3-8-flash","config":"mini_swe_agent_gemini_3_8_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.014173132066358783,"harness":"mini-swe-agent","version":"v1.1","n_passed":330,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":330,"pass_at_1":0.738255033557047,"pass_at_4":0.8584070796460177,"pass_rate":0.738255033557047,"n_attempted":447,"ci_attempted":447,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.362349413758389,"n_tasks_in_set":113,"median_cost_usd":2.1098912999999997,"mean_agent_steps":166.3131991051454,"reasoning_effort":"high","mean_cache_tokens":21456039.230425056,"mean_input_tokens":21734449.25279642,"n_tasks_attempted":113,"mean_output_tokens":143242.6644295302,"median_agent_steps":161,"n_tasks_passed_any":97,"median_input_tokens":18026661,"median_output_tokens":138377,"mean_duration_seconds":686.7691519843399,"median_duration_seconds":604.643838,"median_peak_context_tokens":215558,"median_output_tokens_to_pass":136617.5}},"release_date":"2026-09-02","is_available_on_credits":true},"id":"gemini/gemini-3.8-flash","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":144.2602,"average_ttft":1.8283,"average_latency":4.8719,"uptime_percent":99.1028,"cache_hit_percentage":0.2292},"throughput":{"average_tps":144.2602,"average_ttft":1.8283,"average_latency":4.8719,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"gemini/gemini-flash-latest","base_model_name":"gemini-flash-latest","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"gemini/gemini-flash-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":150.7488,"average_ttft":null,"average_latency":8.7491,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":150.7488,"average_ttft":null,"average_latency":8.7491,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"gemini/gemini-flash-lite-latest","base_model_name":"gemini-flash-lite-latest","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"gemini/gemini-flash-lite-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.7982,"average_ttft":null,"average_latency":0.4396,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7982,"average_ttft":null,"average_latency":0.4396,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"gemini/gemini-pro-latest","base_model_name":"gemini-pro-latest","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"gemini/gemini-pro-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":31.1387,"average_ttft":null,"average_latency":1.9271,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.1387,"average_ttft":null,"average_latency":1.9271,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemma-4-26b-a4b-it","base_model_name":"gemini/gemma-4-26b-a4b-it","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"gemini/gemma-4-26b-a4b-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Gemini AI","provider_id":"google_gemini_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.325457Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"x-goog-api-key","is_scheduled":true,"list_endpoint":"https://generativelanguage.googleapis.com/v1beta/models"},"kind":"host","id":"google_gemini_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gemini/gemma-4-31b-it","base_model_name":"gemini/gemma-4-31b-it","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"gemini/gemma-4-31b-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Gonka24","provider_id":"gonka24","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376944Z","updated_at":"2026-07-23T06:47:03.376962Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.gonka24.com/v1/models"},"kind":"host","id":"gonka24"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gonka24/deepseek-v4-flash-0731","base_model_name":"gonka24/deepseek-v4-flash-0731","max_context_window":399360,"input_cost":0.07,"output_cost":0.14,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"is_available_on_credits":true},"id":"gonka24/deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Gonka24","provider_id":"gonka24","extra_kwargs":{},"created_at":"2026-07-23T06:47:03.376944Z","updated_at":"2026-07-23T06:47:03.376962Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.gonka24.com/v1/models"},"kind":"host","id":"gonka24"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"gonka24/minimax-m2.7","base_model_name":"gonka24/minimax-m2.7","max_context_window":204800,"input_cost":0.018,"output_cost":0.072,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"gonka24/minimax-m2.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/allam-2-7b","base_model_name":"groq/allam-2-7b","max_context_window":4096,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-23","is_available_on_credits":false},"id":"groq/allam-2-7b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/openai/gpt-oss-120b","base_model_name":"groq/openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["groq/openai/gpt-oss-120b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"groq/openai/gpt-oss-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":252.3745,"average_ttft":null,"average_latency":0.9954,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":252.3745,"average_ttft":null,"average_latency":0.9954,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/openai/gpt-oss-20b","base_model_name":"groq/openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["groq/openai/gpt-oss-20b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"groq/openai/gpt-oss-20b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/openai/gpt-oss-safeguard-20b","base_model_name":"","max_context_window":131072,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-29"},"id":"groq/openai/gpt-oss-safeguard-20b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/qwen/qwen3.6-27b","base_model_name":"","max_context_window":131072,"input_cost":0.6,"output_cost":3,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-09"},"id":"groq/qwen/qwen3.6-27b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Groq","provider_id":"groq","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.214022Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.groq.com/openai/v1/models"},"kind":"host","id":"groq"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"groq/qwen/qwen3.8-27b","base_model_name":"","max_context_window":131072,"input_cost":0.8,"output_cost":4,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-17"},"id":"groq/qwen/qwen3.8-27b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inceptron/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"inceptron/deepseek-ai/DeepSeek-V4-Flash-0731","max_context_window":1048576,"input_cost":0.13,"output_cost":0.28,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"is_available_on_credits":false},"id":"inceptron/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inceptron/moonshotai/Kimi-K2.6","base_model_name":"inceptron/moonshotai/Kimi-K2.6","max_context_window":262144,"input_cost":0.73,"output_cost":3.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"inceptron/moonshotai/Kimi-K2.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inceptron/moonshotai/Kimi-K2.7-Code","base_model_name":"inceptron/moonshotai/Kimi-K2.7-Code","max_context_window":262144,"input_cost":0.75,"output_cost":3.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"is_available_on_credits":false},"id":"inceptron/moonshotai/Kimi-K2.7-Code","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"inceptron/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":1048576,"input_cost":1.2,"output_cost":4.2,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"inceptron/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":49.3482,"average_ttft":null,"average_latency":1.3015,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":49.3482,"average_ttft":null,"average_latency":1.3015,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inceptron/zai-org/GLM-5.3","base_model_name":"inceptron/zai-org/GLM-5.3","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"is_available_on_credits":false},"id":"inceptron/zai-org/GLM-5.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inceptron","provider_id":"inceptron","extra_kwargs":{},"created_at":"2026-06-25T00:11:27.917488Z","updated_at":"2026-06-25T00:11:27.917507Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inceptron.io/v1/models"},"kind":"host","id":"inceptron"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inceptron/zai-org/GLM-5.3-Flash","base_model_name":"inceptron/zai-org/GLM-5.3-Flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"is_available_on_credits":false},"id":"inceptron/zai-org/GLM-5.3-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v3.2","base_model_name":"","max_context_window":163840,"input_cost":0.7,"output_cost":2,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/deepseek-v3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":0.8815,"average_ttft":null,"average_latency":2.2917,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.8815,"average_ttft":null,"average_latency":2.2917,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v4-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.23,"output_cost":0.62,"cache_hit_input_cost":0.0028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}}},"id":"inference_net/deepseek-v4-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":0.8513,"average_ttft":null,"average_latency":6.5959,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.8513,"average_ttft":null,"average_latency":6.5959,"number_of_requests":null},"benchmark":{"cost":0.10023560370265487,"intelligence":0.5331858407079646,"latency":1438.9961937522125,"speed":74.83482068364452,"context":201636.5,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v4-flash-0731","base_model_name":"","max_context_window":1048575,"input_cost":0.53,"output_cost":1.58,"cache_hit_input_cost":0.017,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}}},"id":"inference_net/deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.1663,"average_ttft":null,"average_latency":4.8564,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.1663,"average_ttft":null,"average_latency":4.8564,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v4-pro","base_model_name":"","max_context_window":1048576,"input_cost":2.1,"output_cost":4.2,"cache_hit_input_cost":0.003625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"inference_net/deepseek-v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.5652,"average_ttft":null,"average_latency":1.3129,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.5652,"average_ttft":null,"average_latency":1.3129,"number_of_requests":null},"benchmark":{"cost":0.24138687892256638,"intelligence":0.6283185840707964,"latency":2212.510104011062,"speed":47.90889675460797,"context":232374.5,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v4-pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"inference_net/deepseek-v4-pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/deepseek-v4.1-flash","base_model_name":"","max_context_window":1040000,"input_cost":0.3,"output_cost":1,"cache_hit_input_cost":0.007,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/deepseek-v4.1-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.9942,"average_ttft":null,"average_latency":1.7506,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.9942,"average_ttft":null,"average_latency":1.7506,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-2.5-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-2.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.3977,"average_ttft":null,"average_latency":1.3309,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.3977,"average_ttft":null,"average_latency":1.3309,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-2.5-flash-lite","base_model_name":"","max_context_window":1048576,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-2.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.5525,"average_ttft":null,"average_latency":1.8106,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.5525,"average_ttft":null,"average_latency":1.8106,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-2.5-pro","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.6943,"average_ttft":null,"average_latency":7.911,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.6943,"average_ttft":null,"average_latency":7.911,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3-flash-preview","base_model_name":"","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-3-flash-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.6274,"average_ttft":null,"average_latency":1.9455,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.6274,"average_ttft":null,"average_latency":1.9455,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.1-flash-lite","base_model_name":"","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-3.1-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.5777,"average_ttft":null,"average_latency":1.7796,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.5777,"average_ttft":null,"average_latency":1.7796,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.1-pro-preview","base_model_name":"","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}}},"id":"inference_net/gemini-3.1-pro-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.8105,"average_ttft":null,"average_latency":2.8557,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.8105,"average_ttft":null,"average_latency":2.8557,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.5-flash","base_model_name":"","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}}},"id":"inference_net/gemini-3.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.221,"average_ttft":null,"average_latency":1.8444,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.221,"average_ttft":null,"average_latency":1.8444,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.5-flash-lite","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemini-3.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.6239,"average_ttft":null,"average_latency":1.667,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.6239,"average_ttft":null,"average_latency":1.667,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.6-flash","base_model_name":"","max_context_window":1048576,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5038626982845081,"ci_lo":0.4297656202995626,"model":"gemini-3-6-flash","config":"mini_swe_agent_gemini_3_6_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.037048538992472776,"harness":"mini-swe-agent","version":"v1.1","n_passed":211,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":211,"pass_at_1":0.4668141592920354,"pass_at_4":0.7522123893805309,"pass_rate":0.4668141592920354,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.419013277333334,"n_tasks_in_set":113,"median_cost_usd":3.444695325000001,"mean_agent_steps":116.73333333333333,"reasoning_effort":"high","mean_cache_tokens":11254636.448888889,"mean_input_tokens":12595957.344444444,"n_tasks_attempted":113,"mean_output_tokens":95844.86222222222,"median_agent_steps":108,"n_tasks_passed_any":85,"median_input_tokens":8949018.5,"median_output_tokens":86727,"mean_duration_seconds":1477.8607510707964,"median_duration_seconds":1214.8670550000002,"median_peak_context_tokens":151398.5,"median_output_tokens_to_pass":83414}}},"id":"inference_net/gemini-3.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.4273,"average_ttft":null,"average_latency":2.9641,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.4273,"average_ttft":null,"average_latency":2.9641,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemini-3.7-flash","base_model_name":"","max_context_window":1048576,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}}},"id":"inference_net/gemini-3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.2545,"average_ttft":null,"average_latency":1.7806,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.2545,"average_ttft":null,"average_latency":1.7806,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemma-3-27b-it","base_model_name":"","max_context_window":131072,"input_cost":0.09,"output_cost":0.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gemma-3-4b-it","base_model_name":"","max_context_window":131072,"input_cost":0.05,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gemma-3-4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":2.011,"average_ttft":null,"average_latency":1.4918,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.011,"average_ttft":null,"average_latency":1.4918,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/glm-5","base_model_name":"","max_context_window":204800,"input_cost":0.95,"output_cost":2.55,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/glm-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.0931,"average_ttft":null,"average_latency":1.9885,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.0931,"average_ttft":null,"average_latency":1.9885,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/glm-5.2","base_model_name":"","max_context_window":1000000,"input_cost":1.3,"output_cost":4.4,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"inference_net/glm-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.2161,"average_ttft":null,"average_latency":2.6493,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.2161,"average_ttft":null,"average_latency":2.6493,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/glm-5.2-fast","base_model_name":"","max_context_window":1000000,"input_cost":2.6,"output_cost":8.8,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/glm-5.2-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.6663,"average_ttft":null,"average_latency":1.7275,"uptime_percent":100,"cache_hit_percentage":31.25},"throughput":{"average_tps":18.6663,"average_ttft":null,"average_latency":1.7275,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/glm-5.3","base_model_name":"","max_context_window":1048576,"input_cost":0.9,"output_cost":3,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}}},"id":"inference_net/glm-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.7656,"average_ttft":null,"average_latency":1.6721,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7656,"average_ttft":null,"average_latency":1.6721,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/glm-5.3-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.1,"output_cost":0.45,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}}},"id":"inference_net/glm-5.3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.0034,"average_ttft":null,"average_latency":1.7815,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.0034,"average_ttft":null,"average_latency":1.7815,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-4.1","base_model_name":"","max_context_window":1047576,"input_cost":2,"output_cost":8,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.5231,"average_ttft":null,"average_latency":1.9118,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.5231,"average_ttft":null,"average_latency":1.9118,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-4.1-mini","base_model_name":"","max_context_window":1047576,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-4.1-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.7363,"average_ttft":null,"average_latency":1.368,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.7363,"average_ttft":null,"average_latency":1.368,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-4.1-nano","base_model_name":"","max_context_window":1047576,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-4.1-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.4615,"average_ttft":null,"average_latency":2.178,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.4615,"average_ttft":null,"average_latency":2.178,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-4o","base_model_name":"","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-4o","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.8481,"average_ttft":null,"average_latency":1.7294,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.8481,"average_ttft":null,"average_latency":1.7294,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-4o-mini","base_model_name":"","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-4o-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":0.4836,"average_ttft":null,"average_latency":2.3651,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.4836,"average_ttft":null,"average_latency":2.3651,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5-mini","base_model_name":"","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-5-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.4296,"average_ttft":null,"average_latency":2.2442,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.4296,"average_ttft":null,"average_latency":2.2442,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5-nano","base_model_name":"","max_context_window":400000,"input_cost":0.05,"output_cost":0.4,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-5-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.7037,"average_ttft":null,"average_latency":1.63,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.7037,"average_ttft":null,"average_latency":1.63,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5.4","base_model_name":"","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}}},"id":"inference_net/gpt-5.4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.8491,"average_ttft":null,"average_latency":2.2091,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.8491,"average_ttft":null,"average_latency":2.2091,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5.5","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}}},"id":"inference_net/gpt-5.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.2198,"average_ttft":null,"average_latency":2.0936,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.2198,"average_ttft":null,"average_latency":2.0936,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5.6-luna","base_model_name":"","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}}},"id":"inference_net/gpt-5.6-luna","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":2.1777,"average_ttft":null,"average_latency":1.8472,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.1777,"average_ttft":null,"average_latency":1.8472,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5.6-sol","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}}},"id":"inference_net/gpt-5.6-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.898,"average_ttft":null,"average_latency":2.1225,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.898,"average_ttft":null,"average_latency":2.1225,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-5.6-terra","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}}},"id":"inference_net/gpt-5.6-terra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.408,"average_ttft":null,"average_latency":4.1759,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.408,"average_ttft":null,"average_latency":4.1759,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-6-astra","base_model_name":"","max_context_window":922000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7698044042186275,"ci_lo":0.7124964807371247,"model":"gpt-6-astra","config":"mini_swe_agent_gpt_6_astra_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02865396174075141,"harness":"mini-swe-agent","version":"v1.1","n_passed":335,"provider":"openai","ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":335,"pass_at_1":0.7411504424778761,"pass_at_4":0.8053097345132744,"pass_rate":0.7411504424778761,"cost_basis":"Current pricing at all context lengths: $10/M uncached input, $12.50/M cache writes, $1/M cache reads, $50/M output; no separate compute-unit fee.","n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.429117203539823,"n_tasks_in_set":113,"median_cost_usd":3.8406789999999997,"mean_agent_steps":28.754424778761063,"reasoning_effort":"xhigh","mean_cache_tokens":1326921.6836283186,"mean_input_tokens":1456927.0929203539,"n_tasks_attempted":113,"mean_compute_units":752203.0973451327,"mean_output_tokens":29557.327433628318,"median_agent_steps":26,"n_tasks_passed_any":91,"median_input_tokens":1163918.5,"completed_by_attempt":[113,113,113,113],"median_compute_units":662371.5,"median_output_tokens":28542.5,"pass_rate_by_attempt":[0.7079646017699115,0.7345132743362832,0.7787610619469026,0.7433628318584071],"mean_duration_seconds":1132.4004424778761,"mean_reasoning_tokens":11255.66592920354,"mean_cache_read_tokens":1326921.6836283186,"mean_cache_write_tokens":129710.02212389381,"median_duration_seconds":959,"median_reasoning_tokens":10434,"median_cache_read_tokens":1035975,"median_cache_write_tokens":103995,"mean_uncached_input_tokens":295.3871681415929,"median_peak_context_tokens":null,"median_output_tokens_to_pass":28361,"median_uncached_input_tokens":87}}},"id":"inference_net/gpt-6-astra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.7447,"average_ttft":null,"average_latency":2.3038,"uptime_percent":99.9274,"cache_hit_percentage":0},"throughput":{"average_tps":1.7447,"average_ttft":null,"average_latency":2.3038,"number_of_requests":null},"benchmark":{"cost":4.429117203539823,"intelligence":0.7411504424778761,"latency":1132.4004424778761,"speed":26.101479940216276,"context":null,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-6-luna","base_model_name":"","max_context_window":922000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-6-luna","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.2928,"average_ttft":null,"average_latency":5.1638,"uptime_percent":100,"cache_hit_percentage":10.1622},"throughput":{"average_tps":1.2928,"average_ttft":null,"average_latency":5.1638,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/gpt-6-sol","base_model_name":"","max_context_window":922000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/gpt-6-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.7224,"average_ttft":null,"average_latency":2.331,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.7224,"average_ttft":null,"average_latency":2.331,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/grok-4.5","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5604186651978057,"ci_lo":0.5148025737402474,"model":"grok-4-5","config":"mini_swe_agent_grok_4_5_high","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":243,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":243,"pass_at_1":0.5376106194690266,"pass_at_4":0.7787610619469026,"pass_rate":0.5376106194690266,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.4157481725663716,"n_tasks_in_set":113,"median_cost_usd":2.02311,"mean_agent_steps":61.33185840707964,"reasoning_effort":"high","mean_cache_tokens":3943846.5132743362,"mean_input_tokens":4059182.975663717,"n_tasks_attempted":113,"mean_output_tokens":35525.33185840708,"median_agent_steps":56,"n_tasks_passed_any":88,"median_input_tokens":3293744.5,"median_output_tokens":34250,"mean_duration_seconds":484.7029359800885,"median_duration_seconds":430.0852805,"median_peak_context_tokens":94044,"median_output_tokens_to_pass":33872}}},"id":"inference_net/grok-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.4446,"average_ttft":null,"average_latency":1.5087,"uptime_percent":100,"cache_hit_percentage":77.1084},"throughput":{"average_tps":13.4446,"average_ttft":null,"average_latency":1.5087,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/grok-4.6","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.697586806790726,"ci_lo":0.6519707153331677,"model":"grok-4-6","config":"mini_swe_agent_grok_4_6_medium","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":305,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":305,"pass_at_1":0.6747787610619469,"pass_at_4":0.8407079646017699,"pass_rate":0.6747787610619469,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4489837522123894,"n_tasks_in_set":113,"median_cost_usd":2.945834,"mean_agent_steps":70.28982300884955,"reasoning_effort":"medium","mean_cache_tokens":5533327.0088495575,"mean_input_tokens":5725195.139380531,"n_tasks_attempted":113,"mean_output_tokens":49763.99778761062,"median_agent_steps":66,"n_tasks_passed_any":95,"median_input_tokens":4705124,"median_output_tokens":48585.5,"mean_duration_seconds":895.5380579646018,"median_duration_seconds":860.0352045,"median_peak_context_tokens":116622,"median_output_tokens_to_pass":48346}}},"id":"inference_net/grok-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":26.0779,"average_ttft":null,"average_latency":4.7382,"uptime_percent":100,"cache_hit_percentage":80},"throughput":{"average_tps":26.0779,"average_ttft":null,"average_latency":4.7382,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/inference-net/schematron-v2-small","base_model_name":"","max_context_window":128000,"input_cost":0.05,"output_cost":0.23,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/inference-net/schematron-v2-small","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.6,"average_ttft":null,"average_latency":1.8452,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.6,"average_ttft":null,"average_latency":1.8452,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/inference-net/schematron-v2-turbo","base_model_name":"","max_context_window":128000,"input_cost":0.03,"output_cost":0.15,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/inference-net/schematron-v2-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.3818,"average_ttft":null,"average_latency":1.7074,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.3818,"average_ttft":null,"average_latency":1.7074,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/kimi-k2.5","base_model_name":"","max_context_window":262144,"input_cost":0.8,"output_cost":3.95,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/kimi-k2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.7171,"average_ttft":null,"average_latency":3.6017,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.7171,"average_ttft":null,"average_latency":3.6017,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/kimi-k2.6","base_model_name":"","max_context_window":262144,"input_cost":1.25,"output_cost":5.3,"cache_hit_input_cost":0.21,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/kimi-k2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.9234,"average_ttft":null,"average_latency":1.241,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.9234,"average_ttft":null,"average_latency":1.241,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/kimi-k3-fast","base_model_name":"","max_context_window":1048576,"input_cost":4.5,"output_cost":22.5,"cache_hit_input_cost":0.45,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/kimi-k3-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.677,"average_ttft":null,"average_latency":1.667,"uptime_percent":100,"cache_hit_percentage":49.4565},"throughput":{"average_tps":19.677,"average_ttft":null,"average_latency":1.667,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/llama-3.2-1b-instruct","base_model_name":"","max_context_window":60000,"input_cost":0.027,"output_cost":0.201,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/llama-3.2-1b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.8164,"average_ttft":null,"average_latency":1.1086,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.8164,"average_ttft":null,"average_latency":1.1086,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/llama-3.2-3b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.05,"output_cost":0.33,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/llama-3.2-3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.8382,"average_ttft":null,"average_latency":1.3602,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.8382,"average_ttft":null,"average_latency":1.3602,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/llama-3.3-70b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.13,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/llama-3.3-70b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":2.3806,"average_ttft":null,"average_latency":0.8478,"uptime_percent":100,"cache_hit_percentage":30.1887},"throughput":{"average_tps":2.3806,"average_ttft":null,"average_latency":0.8478,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/moonshotai/kimi-k3","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}}},"id":"inference_net/moonshotai/kimi-k3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.0095,"average_ttft":null,"average_latency":1.5949,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.0095,"average_ttft":null,"average_latency":1.5949,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/nemotron-3-super","base_model_name":"","max_context_window":262144,"input_cost":0.102,"output_cost":0.48,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/nemotron-3-super","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.026,"average_ttft":null,"average_latency":3.4469,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.026,"average_ttft":null,"average_latency":3.4469,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/qwen3-14b","base_model_name":"","max_context_window":131072,"input_cost":0.2275,"output_cost":0.91,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/qwen3-14b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.7658,"average_ttft":null,"average_latency":2.4214,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.7658,"average_ttft":null,"average_latency":2.4214,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/qwen3-30b-a3b","base_model_name":"","max_context_window":40960,"input_cost":0.12,"output_cost":0.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/qwen3-30b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.2842,"average_ttft":null,"average_latency":2.8372,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.2842,"average_ttft":null,"average_latency":2.8372,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/qwen3-8b","base_model_name":"","max_context_window":131072,"input_cost":0.117,"output_cost":0.455,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/qwen3-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":38.9516,"average_ttft":null,"average_latency":2.7533,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.9516,"average_ttft":null,"average_latency":2.7533,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/qwen3-max-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.78,"output_cost":3.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/qwen3-max-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":0.7234,"average_ttft":null,"average_latency":1.4082,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":0.7234,"average_ttft":null,"average_latency":1.4082,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Inference.net","provider_id":"inference_net","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.345874Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.inference.net/v1/models"},"kind":"host","id":"inference_net"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"inference_net/qwen3.7-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"inference_net/qwen3.7-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":29.6549,"average_ttft":null,"average_latency":5.958,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":29.6549,"average_ttft":null,"average_latency":5.958,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/deepseek-ai/DeepSeek-R1-0528","base_model_name":"deepseek-ai/DeepSeek-R1-0528","max_context_window":128000,"input_cost":0.53025,"output_cost":2.1915,"cache_hit_input_cost":0.265125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek-ai/DeepSeek-R1-0528"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-20"},"id":"ionet/deepseek-ai/DeepSeek-R1-0528","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.2455,"average_ttft":null,"average_latency":4.9945,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.2455,"average_ttft":null,"average_latency":4.9945,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/deepseek-ai/DeepSeek-V3.2","base_model_name":"deepseek-ai/DeepSeek-V3.2","max_context_window":163840,"input_cost":0.87758,"output_cost":1.57552,"cache_hit_input_cost":0.43879,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2025-12-01"},"id":"ionet/deepseek-ai/DeepSeek-V3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.208,"average_ttft":null,"average_latency":1.6356,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.208,"average_ttft":null,"average_latency":1.6356,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"deepseek-ai/DeepSeek-V4-Flash","max_context_window":1048576,"input_cost":0.1428,"output_cost":0.2916,"cache_hit_input_cost":0.0714,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"ionet/deepseek-ai/DeepSeek-V4-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.4275,"average_ttft":null,"average_latency":1.1592,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.4275,"average_ttft":null,"average_latency":1.1592,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"deepseek-ai/DeepSeek-V4-Pro","max_context_window":1048576,"input_cost":1.7508,"output_cost":3.5416,"cache_hit_input_cost":0.8754,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24"},"id":"ionet/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":48.9645,"average_ttft":null,"average_latency":1.3303,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.9645,"average_ttft":null,"average_latency":1.3303,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/google/gemma-4-26b-a4b-it","base_model_name":"google/gemma-4-26b-a4b-it","max_context_window":262142,"input_cost":0.1165,"output_cost":0.388,"cache_hit_input_cost":0.05825,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"ionet/google/gemma-4-26b-a4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":55.251,"average_ttft":1.1616,"average_latency":1.1114,"uptime_percent":100,"cache_hit_percentage":49.8334},"throughput":{"average_tps":55.251,"average_ttft":1.1616,"average_latency":1.1114,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","base_model_name":"Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","max_context_window":106000,"input_cost":0.531,"output_cost":2.605,"cache_hit_input_cost":0.2655,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"ionet/Intel/Qwen3-Coder-480B-A35B-Instruct-int4-mixed-ar","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.9526,"average_ttft":null,"average_latency":0.9101,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.9526,"average_ttft":null,"average_latency":0.9101,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/meta-llama/Llama-3.3-70B-Instruct","base_model_name":"meta-llama/Llama-3.3-70B-Instruct","max_context_window":128000,"input_cost":0.668,"output_cost":0.828,"cache_hit_input_cost":0.334,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/Llama-3.3-70B-Instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06"},"id":"ionet/meta-llama/Llama-3.3-70B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":46.1603,"average_ttft":null,"average_latency":0.51,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":46.1603,"average_ttft":null,"average_latency":0.51,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","base_model_name":"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","max_context_window":430000,"input_cost":0.35,"output_cost":1.08,"cache_hit_input_cost":0.175,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-05"},"id":"ionet/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.7811,"average_ttft":null,"average_latency":0.7401,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.7811,"average_ttft":null,"average_latency":0.7401,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/MiniMaxAI/MiniMax-M2.5","base_model_name":"MiniMaxAI/MiniMax-M2.5","max_context_window":196600,"input_cost":0.294,"output_cost":1.176,"cache_hit_input_cost":0.147,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-12"},"id":"ionet/MiniMaxAI/MiniMax-M2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":53.8749,"average_ttft":null,"average_latency":0.7883,"uptime_percent":100,"cache_hit_percentage":82.0513},"throughput":{"average_tps":53.8749,"average_ttft":null,"average_latency":0.7883,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/MiniMaxAI/MiniMax-M2.7","base_model_name":"MiniMaxAI/MiniMax-M2.7","max_context_window":204800,"input_cost":0.42,"output_cost":1.68,"cache_hit_input_cost":0.21,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"ionet/MiniMaxAI/MiniMax-M2.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/mistralai/Mistral-Nemo-Instruct-2407","base_model_name":"mistralai/Mistral-Nemo-Instruct-2407","max_context_window":128000,"input_cost":0.0575,"output_cost":0.0975,"cache_hit_input_cost":0.02875,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["mistralai/Mistral-Nemo-Instruct-2407"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-18"},"id":"ionet/mistralai/Mistral-Nemo-Instruct-2407","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.5149,"average_ttft":null,"average_latency":0.7993,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.5149,"average_ttft":null,"average_latency":0.7993,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/moonshotai/Kimi-K2-Instruct-0905","base_model_name":"moonshotai/Kimi-K2-Instruct-0905","max_context_window":262144,"input_cost":0.57,"output_cost":2.3,"cache_hit_input_cost":0.285,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"ionet/moonshotai/Kimi-K2-Instruct-0905","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.3077,"average_ttft":null,"average_latency":1.2334,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.3077,"average_ttft":null,"average_latency":1.2334,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/moonshotai/Kimi-K2-Thinking","base_model_name":"moonshotai/Kimi-K2-Thinking","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"ionet/moonshotai/Kimi-K2-Thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.6241,"average_ttft":null,"average_latency":3.2622,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.6241,"average_ttft":null,"average_latency":3.2622,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/moonshotai/Kimi-K2.5","base_model_name":"moonshotai/Kimi-K2.5","max_context_window":262144,"input_cost":0.522,"output_cost":2.69,"cache_hit_input_cost":0.261,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"ionet/moonshotai/Kimi-K2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.9958,"average_ttft":null,"average_latency":2.3733,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.9958,"average_ttft":null,"average_latency":2.3733,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/moonshotai/Kimi-K2.6","base_model_name":"moonshotai/Kimi-K2.6","max_context_window":262142,"input_cost":0.8555,"output_cost":3.78,"cache_hit_input_cost":0.42775,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"ionet/moonshotai/Kimi-K2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":91.0943,"average_ttft":null,"average_latency":0.6891,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":91.0943,"average_ttft":null,"average_latency":0.6891,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.168,"output_cost":0.63,"cache_hit_input_cost":0.084,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"ionet/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":82.6997,"average_ttft":null,"average_latency":0.7851,"uptime_percent":100,"cache_hit_percentage":45.7143},"throughput":{"average_tps":82.6997,"average_ttft":null,"average_latency":0.7851,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":64000,"input_cost":0.073,"output_cost":0.27,"cache_hit_input_cost":0.0365,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"ionet/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":62.3171,"average_ttft":null,"average_latency":1.0048,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":62.3171,"average_ttft":null,"average_latency":1.0048,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/Qwen/Qwen3-Next-80B-A3B-Instruct","base_model_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","max_context_window":262144,"input_cost":0.1175,"output_cost":1.136,"cache_hit_input_cost":0.05875,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"ionet/Qwen/Qwen3-Next-80B-A3B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":27.9733,"average_ttft":null,"average_latency":1.1083,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.9733,"average_ttft":null,"average_latency":1.1083,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/Qwen/Qwen3.6-27B","base_model_name":"Qwen/Qwen3.6-27B","max_context_window":262140,"input_cost":0.3358,"output_cost":2.94,"cache_hit_input_cost":0.1679,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"ionet/Qwen/Qwen3.6-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":27.1634,"average_ttft":null,"average_latency":4.0101,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.1634,"average_ttft":null,"average_latency":4.0101,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/Qwen/Qwen3.6-35B-A3B","base_model_name":"Qwen/Qwen3.6-35B-A3B","max_context_window":262140,"input_cost":0.184,"output_cost":1.21,"cache_hit_input_cost":0.092,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"ionet/Qwen/Qwen3.6-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":44.4709,"average_ttft":null,"average_latency":4.8255,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":44.4709,"average_ttft":null,"average_latency":4.8255,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-4.5-Air","base_model_name":"zai-org/GLM-4.5-Air","max_context_window":131070,"input_cost":0.156667,"output_cost":0.936667,"cache_hit_input_cost":0.078334,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"ionet/zai-org/GLM-4.5-Air","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":41.3758,"average_ttft":null,"average_latency":1.5636,"uptime_percent":100,"cache_hit_percentage":66.6667},"throughput":{"average_tps":41.3758,"average_ttft":null,"average_latency":1.5636,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-4.6","base_model_name":"zai-org/GLM-4.6","max_context_window":131072,"input_cost":0.85,"output_cost":2.75,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-30"},"id":"ionet/zai-org/GLM-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":19.1149,"average_ttft":null,"average_latency":3.5144,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.1149,"average_ttft":null,"average_latency":3.5144,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-4.7","base_model_name":"zai-org/GLM-4.7","max_context_window":202752,"input_cost":0.874,"output_cost":2.33,"cache_hit_input_cost":0.437,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"ionet/zai-org/GLM-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":27.3348,"average_ttft":null,"average_latency":6.659,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.3348,"average_ttft":null,"average_latency":6.659,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-4.7-Flash","base_model_name":"zai-org/GLM-4.7-Flash","max_context_window":200000,"input_cost":0.0831,"output_cost":0.426,"cache_hit_input_cost":0.04155,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"ionet/zai-org/GLM-4.7-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.3023,"average_ttft":null,"average_latency":5.5255,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.3023,"average_ttft":null,"average_latency":5.5255,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-5","base_model_name":"zai-org/GLM-5","max_context_window":202752,"input_cost":0.92,"output_cost":2.976,"cache_hit_input_cost":0.46,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-11"},"id":"ionet/zai-org/GLM-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":40.7636,"average_ttft":null,"average_latency":1.6238,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":40.7636,"average_ttft":null,"average_latency":1.6238,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-5.1","base_model_name":"zai-org/GLM-5.1","max_context_window":202750,"input_cost":1.38,"output_cost":4.38,"cache_hit_input_cost":0.69,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"ionet/zai-org/GLM-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":60.7154,"average_ttft":null,"average_latency":1.0551,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":60.7154,"average_ttft":null,"average_latency":1.0551,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"IO.net","provider_id":"ionet","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175685Z","updated_at":"2026-06-06T08:37:06.175689Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"ionet"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"ionet/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":262144,"input_cost":1.36,"output_cost":4.36,"cache_hit_input_cost":0.68,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"ionet/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.1107,"average_ttft":null,"average_latency":2.0961,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.1107,"average_ttft":null,"average_latency":2.0961,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Makora","provider_id":"makora","extra_kwargs":{},"created_at":"2026-07-14T07:05:56.784793Z","updated_at":"2026-07-14T07:05:56.784805Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.makora.com/v1/models"},"kind":"host","id":"makora"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"makora/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"deepseek-ai/DeepSeek-V4-Flash","max_context_window":1000000,"input_cost":0.09,"output_cost":0.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":0.1,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"makora/deepseek-ai/DeepSeek-V4-Flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":89.4608,"average_ttft":null,"average_latency":3.4054,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":89.4608,"average_ttft":null,"average_latency":3.4054,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Makora","provider_id":"makora","extra_kwargs":{},"created_at":"2026-07-14T07:05:56.784793Z","updated_at":"2026-07-14T07:05:56.784805Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.makora.com/v1/models"},"kind":"host","id":"makora"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"makora/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"makora/deepseek-ai/DeepSeek-V4.1-Flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"makora/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Makora","provider_id":"makora","extra_kwargs":{},"created_at":"2026-07-14T07:05:56.784793Z","updated_at":"2026-07-14T07:05:56.784805Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.makora.com/v1/models"},"kind":"host","id":"makora"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"makora/google/gemma-4-26B-A4B","base_model_name":"google/gemma-4-26B-A4B","max_context_window":256000,"input_cost":0.1,"output_cost":0.34,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":0.1,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"makora/google/gemma-4-26B-A4B","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":114.2211,"average_ttft":0.6832,"average_latency":1.4417,"uptime_percent":100,"cache_hit_percentage":49.6423},"throughput":{"average_tps":114.2211,"average_ttft":0.6832,"average_latency":1.4417,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Makora","provider_id":"makora","extra_kwargs":{},"created_at":"2026-07-14T07:05:56.784793Z","updated_at":"2026-07-14T07:05:56.784805Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.makora.com/v1/models"},"kind":"host","id":"makora"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"makora/moonshotai/Kimi-K3","base_model_name":"moonshotai/Kimi-K3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":0.15,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16"},"id":"makora/moonshotai/Kimi-K3","is_byok":false,"effective_discount_rate":0.15,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.869,"average_ttft":0.7057,"average_latency":12.4808,"uptime_percent":100,"cache_hit_percentage":52.7847},"throughput":{"average_tps":30.869,"average_ttft":0.7057,"average_latency":12.4808,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Makora","provider_id":"makora","extra_kwargs":{},"created_at":"2026-07-14T07:05:56.784793Z","updated_at":"2026-07-14T07:05:56.784805Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://inference.makora.com/v1/models"},"kind":"host","id":"makora"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"makora/zai-org/GLM-5.3","base_model_name":"makora/zai-org/GLM-5.3","max_context_window":980000,"input_cost":1.05,"output_cost":4.2,"cache_hit_input_cost":0.19,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"is_available_on_credits":false},"id":"makora/zai-org/GLM-5.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Meta","provider_id":"meta","extra_kwargs":{},"created_at":"2026-09-08T07:49:20.224428Z","updated_at":"2026-09-08T07:49:20.224447Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"meta"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"meta/muse-spark-1.3","base_model_name":"muse-spark-1.3","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-02","is_available_on_credits":true},"id":"meta/muse-spark-1.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10411.051,"average_ttft":5.6739,"average_latency":5.3446,"uptime_percent":92.3077,"cache_hit_percentage":0},"throughput":{"average_tps":10411.051,"average_ttft":5.6739,"average_latency":5.3446,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2","base_model_name":"MiniMax-M2","max_context_window":200000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-27"},"id":"minimax/MiniMax-M2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":46.7782,"average_ttft":0.6704,"average_latency":1.5085,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":46.7782,"average_ttft":0.6704,"average_latency":1.5085,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.1","base_model_name":"MiniMax-M2.1","max_context_window":200000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23"},"id":"minimax/MiniMax-M2.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":42.2336,"average_ttft":null,"average_latency":1.4709,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.2336,"average_ttft":null,"average_latency":1.4709,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.1-highspeed","base_model_name":"MiniMax-M2.1-highspeed","max_context_window":204800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23"},"id":"minimax/MiniMax-M2.1-highspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.6399,"average_ttft":null,"average_latency":2.2471,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.6399,"average_ttft":null,"average_latency":2.2471,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.5","base_model_name":"MiniMax-M2.5","max_context_window":200000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"minimax/MiniMax-M2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":36.1802,"average_ttft":null,"average_latency":1.5906,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.1802,"average_ttft":null,"average_latency":1.5906,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.5-highspeed","base_model_name":"MiniMax-M2.5-highspeed","max_context_window":204800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-13"},"id":"minimax/MiniMax-M2.5-highspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.6686,"average_ttft":null,"average_latency":1.368,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.6686,"average_ttft":null,"average_latency":1.368,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.7","base_model_name":"MiniMax-M2.7","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"minimax/MiniMax-M2.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.7218,"average_ttft":null,"average_latency":2.293,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.7218,"average_ttft":null,"average_latency":2.293,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M2.7-highspeed","base_model_name":"MiniMax-M2.7-highspeed","max_context_window":204800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"minimax/MiniMax-M2.7-highspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.6345,"average_ttft":null,"average_latency":2.5328,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.6345,"average_ttft":null,"average_latency":2.5328,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MiniMax","provider_id":"minimax","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175638Z","updated_at":"2026-06-06T08:37:06.175643Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.minimax.io/v1/models"},"kind":"host","id":"minimax"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"minimax/MiniMax-M3","base_model_name":"MiniMax-M3","max_context_window":1000000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-01"},"id":"minimax/MiniMax-M3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":55.7054,"average_ttft":null,"average_latency":2.4396,"uptime_percent":100,"cache_hit_percentage":72.3164},"throughput":{"average_tps":55.7054,"average_ttft":null,"average_latency":2.4396,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/codestral-2508","base_model_name":"codestral-2508","max_context_window":256000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-01"},"id":"mistral/codestral-2508","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.3113,"average_ttft":null,"average_latency":0.4592,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.3113,"average_ttft":null,"average_latency":0.4592,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/codestral-latest","base_model_name":"codestral-latest","max_context_window":256000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/codestral-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.3261,"average_ttft":null,"average_latency":0.6311,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3261,"average_ttft":null,"average_latency":0.6311,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/labs-leanstral-1-5","base_model_name":"mistral/labs-leanstral-1-5","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-30","is_available_on_credits":false},"id":"mistral/labs-leanstral-1-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/labs-leanstral-1-5-1","base_model_name":"mistral/labs-leanstral-1-5-1","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"mistral/labs-leanstral-1-5-1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/magistral-medium-latest","base_model_name":"magistral-medium-latest","max_context_window":262144,"input_cost":2,"output_cost":5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-17"},"id":"mistral/magistral-medium-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.7232,"average_ttft":null,"average_latency":0.4838,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7232,"average_ttft":null,"average_latency":0.4838,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/magistral-small-latest","base_model_name":"magistral-small-latest","max_context_window":262144,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-17"},"id":"mistral/magistral-small-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":108.9388,"average_ttft":0.3386,"average_latency":0.4605,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":108.9388,"average_ttft":0.3386,"average_latency":0.4605,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-14b-2512","base_model_name":"ministral-14b-2512","max_context_window":262144,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"mistral/ministral-14b-2512","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.5123,"average_ttft":null,"average_latency":1.1872,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.5123,"average_ttft":null,"average_latency":1.1872,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-14b-latest","base_model_name":"ministral-14b-latest","max_context_window":262144,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/ministral-14b-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":43.7515,"average_ttft":null,"average_latency":1.0396,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":43.7515,"average_ttft":null,"average_latency":1.0396,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-3b-2512","base_model_name":"ministral-3b-2512","max_context_window":131072,"input_cost":0.1,"output_cost":0.1,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-16"},"id":"mistral/ministral-3b-2512","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":122.7131,"average_ttft":null,"average_latency":0.4366,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":122.7131,"average_ttft":null,"average_latency":0.4366,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-3b-latest","base_model_name":"ministral-3b-latest","max_context_window":131072,"input_cost":0.1,"output_cost":0.1,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-16"},"id":"mistral/ministral-3b-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":59.646,"average_ttft":null,"average_latency":0.8451,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":59.646,"average_ttft":null,"average_latency":0.8451,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-8b-2512","base_model_name":"ministral-8b-2512","max_context_window":262144,"input_cost":0.15,"output_cost":0.15,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-16"},"id":"mistral/ministral-8b-2512","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":74,"average_ttft":null,"average_latency":0.8771,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":74,"average_ttft":null,"average_latency":0.8771,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/ministral-8b-latest","base_model_name":"ministral-8b-latest","max_context_window":262144,"input_cost":0.15,"output_cost":0.15,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-16"},"id":"mistral/ministral-8b-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":72.6806,"average_ttft":null,"average_latency":0.6752,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":72.6806,"average_ttft":null,"average_latency":0.6752,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-code-fim-latest","base_model_name":"mistral/mistral-code-fim-latest","max_context_window":256000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-30","is_available_on_credits":false},"id":"mistral/mistral-code-fim-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.2411,"average_ttft":null,"average_latency":0.4161,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.2411,"average_ttft":null,"average_latency":0.4161,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-code-latest","base_model_name":"mistral/mistral-code-latest","max_context_window":256000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-04","is_available_on_credits":false},"id":"mistral/mistral-code-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":34.7867,"average_ttft":null,"average_latency":0.3737,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.7867,"average_ttft":null,"average_latency":0.3737,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1.5,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-medium","base_model_name":"mistral/mistral-medium","max_context_window":262144,"input_cost":2.73,"output_cost":8.2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["mistral/mistral-medium"],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/mistral-medium","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.9397,"average_ttft":null,"average_latency":0.3256,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.9397,"average_ttft":null,"average_latency":0.3256,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-medium-2604","base_model_name":"mistral-medium-2604","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/mistral-medium-2604","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.5548,"average_ttft":null,"average_latency":0.3759,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.5548,"average_ttft":null,"average_latency":0.3759,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-medium-3","base_model_name":"mistral-medium-3","max_context_window":262144,"input_cost":0.4,"output_cost":2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-05-07"},"id":"mistral/mistral-medium-3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.9226,"average_ttft":null,"average_latency":0.3739,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.9226,"average_ttft":null,"average_latency":0.3739,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-medium-3-5","base_model_name":"mistral-medium-3-5","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-30"},"id":"mistral/mistral-medium-3-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.3996,"average_ttft":null,"average_latency":0.3931,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.3996,"average_ttft":null,"average_latency":0.3931,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-medium-3.5","base_model_name":"mistral-medium-3.5","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/mistral-medium-3.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":33.1811,"average_ttft":null,"average_latency":0.3452,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":33.1811,"average_ttft":null,"average_latency":0.3452,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-medium-latest","base_model_name":"mistral-medium-latest","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-28"},"id":"mistral/mistral-medium-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.4705,"average_ttft":null,"average_latency":0.3899,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.4705,"average_ttft":null,"average_latency":0.3899,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-small-2603","base_model_name":"mistral-small-2603","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-16"},"id":"mistral/mistral-small-2603","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":35.9761,"average_ttft":null,"average_latency":0.3636,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.9761,"average_ttft":null,"average_latency":0.3636,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/mistral-small-latest","base_model_name":"mistral-small-latest","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"mistral/mistral-small-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":107.9591,"average_ttft":0.3785,"average_latency":0.5167,"uptime_percent":100,"cache_hit_percentage":9.572},"throughput":{"average_tps":107.9591,"average_ttft":0.3785,"average_latency":0.5167,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-vibe-cli-fast","base_model_name":"mistral/mistral-vibe-cli-fast","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"mistral/mistral-vibe-cli-fast","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-vibe-cli-latest","base_model_name":"mistral/mistral-vibe-cli-latest","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"mistral/mistral-vibe-cli-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"mistral/mistral-vibe-cli-with-tools","base_model_name":"mistral/mistral-vibe-cli-with-tools","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"mistral/mistral-vibe-cli-with-tools","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/voxtral-small-2507","base_model_name":"voxtral-small-2507","max_context_window":32768,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-14"},"id":"mistral/voxtral-small-2507","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":99.4703,"average_ttft":null,"average_latency":0.6435,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":99.4703,"average_ttft":null,"average_latency":0.6435,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Mistral","provider_id":"mistral","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.681365Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.mistral.ai/v1/models"},"kind":"host","id":"mistral"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"mistral/voxtral-small-latest","base_model_name":"voxtral-small-latest","max_context_window":32768,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-14"},"id":"mistral/voxtral-small-latest","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":88.0645,"average_ttft":null,"average_latency":0.7398,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":88.0645,"average_ttft":null,"average_latency":0.7398,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Moonshot","provider_id":"moonshot","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.814178Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.moonshot.ai/v1/models"},"kind":"host","id":"moonshot"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"moonshot/kimi-k2.6","base_model_name":"kimi-k2.6","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"moonshot/kimi-k2.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Moonshot","provider_id":"moonshot","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.814178Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.moonshot.ai/v1/models"},"kind":"host","id":"moonshot"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"moonshot/kimi-k2.7-code","base_model_name":"moonshot/kimi-k2.7-code","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.19,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"context_size":262144,"fixed_sampling":{"n":1,"top_p":0.95,"temperature":1},"reasoning_mode":"always_on","discovery_run_id":"provider-models-platform-deepseek-minimax-moonshot-20260807T155933Z","input_modalities":["text","image","video"],"output_modalities":["text"],"is_available_on_credits":false,"default_max_output_tokens":32768},"id":"moonshot/kimi-k2.7-code","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Moonshot","provider_id":"moonshot","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.814178Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.moonshot.ai/v1/models"},"kind":"host","id":"moonshot"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"moonshot/kimi-k2.7-code-highspeed","base_model_name":"moonshot/kimi-k2.7-code-highspeed","max_context_window":262144,"input_cost":1.9,"output_cost":8,"cache_hit_input_cost":0.38,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"variant":"highspeed","benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"context_size":262144,"fixed_sampling":{"n":1,"top_p":0.95,"temperature":1},"reasoning_mode":"always_on","discovery_run_id":"provider-models-platform-deepseek-minimax-moonshot-20260807T155933Z","input_modalities":["text","image","video"],"output_modalities":["text"],"is_available_on_credits":false,"default_max_output_tokens":32768,"typical_output_tokens_per_second":180,"short_context_output_tokens_per_second_max":260},"id":"moonshot/kimi-k2.7-code-highspeed","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Moonshot","provider_id":"moonshot","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.814178Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.moonshot.ai/v1/models"},"kind":"host","id":"moonshot"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"moonshot/kimi-k3","base_model_name":"moonshot/kimi-k3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"context_size":1048576,"reasoning_mode":"always_on","discovery_run_id":"provider-models-platform-deepseek-minimax-moonshot-20260807T155933Z","input_modalities":["text","image","video"],"max_output_tokens":1048576,"output_modalities":["text"],"reasoning_efforts":["low","high","max"],"access_requirements":{"minimum_top_up_usd":1},"is_available_on_credits":false,"default_reasoning_effort":"max","default_max_output_tokens":131072},"id":"moonshot/kimi-k3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":{"cost":4.654682129933482,"intelligence":0.6851441241685144,"latency":4541.447376412417,"speed":17.94578596140072,"context":130945,"passAt4":0.8938053097345132}},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/deepseek/deepseek-v4-flash","base_model_name":"morph/deepseek/deepseek-v4-flash","max_context_window":1048576,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04","prompt_logging":true,"prompt_training":true,"zero_data_retention":true,"is_available_on_credits":false},"id":"morph/deepseek/deepseek-v4-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/deepseek/deepseek-v4-flash-0731","base_model_name":"morph/deepseek/deepseek-v4-flash-0731","max_context_window":1048576,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04","prompt_logging":true,"prompt_training":true,"zero_data_retention":true,"is_available_on_credits":false},"id":"morph/deepseek/deepseek-v4-flash-0731","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/deepseek/deepseek-v4-flash-20260423","base_model_name":"morph/deepseek/deepseek-v4-flash-20260423","max_context_window":1048576,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04","prompt_logging":true,"prompt_training":true,"zero_data_retention":true,"is_available_on_credits":false},"id":"morph/deepseek/deepseek-v4-flash-20260423","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-dsv41flash","base_model_name":"morph/morph-dsv41flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.003,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"morph/morph-dsv41flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"morph/morph-dsv4flash","base_model_name":"morph/morph-dsv4flash","max_context_window":1048576,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_hit_input_cost","display_name","input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04","prompt_logging":true,"prompt_training":true,"zero_data_retention":true},"id":"morph/morph-dsv4flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-dsv4flash-0731","base_model_name":"morph/morph-dsv4flash-0731","max_context_window":1048576,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","display_name","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04","prompt_logging":true,"prompt_training":true,"zero_data_retention":true,"is_available_on_credits":false},"id":"morph/morph-dsv4flash-0731","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"morph/morph-glm52-744b","base_model_name":"morph/morph-glm52-744b","max_context_window":1000000,"input_cost":1.1,"output_cost":4.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"context_size":1000000,"release_date":"2026-06-13","prompt_logging":true,"prompt_training":true,"zero_data_retention":true},"id":"morph/morph-glm52-744b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.87,"average_ttft":null,"average_latency":3.7923,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.87,"average_ttft":null,"average_latency":3.7923,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-glm53-744b","base_model_name":"morph/morph-glm53-744b","max_context_window":1048576,"input_cost":1.19,"output_cost":3.74,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"is_available_on_credits":false},"id":"morph/morph-glm53-744b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-glm53flash","base_model_name":"morph/morph-glm53flash","max_context_window":1048576,"input_cost":0.1,"output_cost":0.35,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"is_available_on_credits":false},"id":"morph/morph-glm53flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-kimik3","base_model_name":"morph/morph-kimik3","max_context_window":1048576,"input_cost":2.5,"output_cost":14,"cache_hit_input_cost":0.29,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"is_available_on_credits":false},"id":"morph/morph-kimik3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"morph/morph-kimik3-fast","base_model_name":"morph/morph-kimik3-fast","max_context_window":1048576,"input_cost":6,"output_cost":22.5,"cache_hit_input_cost":0.6,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","display_name","input_cost","max_context_window","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":false,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"morph/morph-kimik3-fast","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"morph/morph-v3-fast","base_model_name":"morph/morph-v3-fast","max_context_window":262144,"input_cost":0.8,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-07","prompt_logging":true,"prompt_training":true,"zero_data_retention":true},"id":"morph/morph-v3-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3670.512,"average_ttft":null,"average_latency":4.5222,"uptime_percent":100,"cache_hit_percentage":89.8876},"throughput":{"average_tps":3670.512,"average_ttft":null,"average_latency":4.5222,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"MorphLLM","provider_id":"morphllm","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175591Z","updated_at":"2026-06-06T08:37:06.175595Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.morphllm.com/v1/models"},"kind":"host","id":"morphllm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"morph/morph-v3-large","base_model_name":"morph/morph-v3-large","max_context_window":262144,"input_cost":0.9,"output_cost":1.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-07","prompt_logging":true,"prompt_training":true,"zero_data_retention":true},"id":"morph/morph-v3-large","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.6646,"average_ttft":null,"average_latency":0.3531,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.6646,"average_ttft":null,"average_latency":0.3531,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"","max_context_window":1024000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-08-13"},"id":"nebius/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"","max_context_window":1048576,"input_cost":1.75,"output_cost":3.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"nebius/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"","max_context_window":979000,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-09-10"},"id":"nebius/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"","max_context_window":1048000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-15"},"id":"nebius/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/google/gemma-3-27b-it","base_model_name":"","max_context_window":110000,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nebius/google/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/MiniMaxAI/MiniMax-M3","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-31"},"id":"nebius/MiniMaxAI/MiniMax-M3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/moonshotai/Kimi-K2.6","base_model_name":"","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-12"},"id":"nebius/moonshotai/Kimi-K2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/moonshotai/Kimi-K2.7-Code","base_model_name":"","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"release_date":"2026-06-18"},"id":"nebius/moonshotai/Kimi-K2.7-Code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/moonshotai/Kimi-K3","base_model_name":"","max_context_window":1024000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-27"},"id":"nebius/moonshotai/Kimi-K3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/NousResearch/Hermes-4-405B","base_model_name":"","max_context_window":131072,"input_cost":1,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nebius/NousResearch/Hermes-4-405B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/nvidia/Nemotron-3_5-Lightning","base_model_name":"","max_context_window":1048576,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27"},"id":"nebius/nvidia/Nemotron-3_5-Lightning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":133.5476,"average_ttft":null,"average_latency":1.1082,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":133.5476,"average_ttft":null,"average_latency":1.1082,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/nvidia/nemotron-3-super-120b-a12b","base_model_name":"","max_context_window":262144,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-11"},"id":"nebius/nvidia/nemotron-3-super-120b-a12b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","base_model_name":"","max_context_window":1048576,"input_cost":1,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-04"},"id":"nebius/nvidia/Nemotron-3-Ultra-550b-a55b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","base_model_name":"","max_context_window":262144,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-15"},"id":"nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":56.5905,"average_ttft":null,"average_latency":0.9012,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.5905,"average_ttft":null,"average_latency":0.9012,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openai/gpt-oss-120b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"nebius/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":114.8377,"average_ttft":null,"average_latency":0.4872,"uptime_percent":100,"cache_hit_percentage":94.1176},"throughput":{"average_tps":114.8377,"average_ttft":null,"average_latency":0.4872,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/openbmb/MiniCPM-V-4_5","base_model_name":"","max_context_window":32000,"input_cost":0.658,"output_cost":1.11,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-01"},"id":"nebius/openbmb/MiniCPM-V-4_5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","base_model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","max_context_window":262144,"input_cost":0.2,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Qwen/Qwen3-235B-A22B-Instruct-2507"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":41000,"release_date":"2025-07-21","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"nebius/Qwen/Qwen3-235B-A22B-Instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.212,"average_ttft":null,"average_latency":2.2506,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.212,"average_ttft":null,"average_latency":2.2506,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","base_model_name":"","max_context_window":262144,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nebius/Qwen/Qwen3-30B-A3B-Instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/Qwen/Qwen3-Embedding-8B","base_model_name":"","max_context_window":40960,"input_cost":0.01,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"embedding","metadata":{},"id":"nebius/Qwen/Qwen3-Embedding-8B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/Qwen/Qwen3.5-397B-A17B","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-17"},"id":"nebius/Qwen/Qwen3.5-397B-A17B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/Qwen/Qwen3.8-27B","base_model_name":"","max_context_window":262144,"input_cost":0.45,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nebius/Qwen/Qwen3.8-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/zai-org/GLM-5.1","base_model_name":"","max_context_window":202752,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nebius/zai-org/GLM-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/zai-org/GLM-5.2","base_model_name":"","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-15"},"id":"nebius/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/zai-org/GLM-5.3","base_model_name":"","max_context_window":1024000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-09-11"},"id":"nebius/zai-org/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nebius","provider_id":"nebius","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.103583Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.tokenfactory.nebius.com/v1/models"},"kind":"host","id":"nebius"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nebius/zai-org/GLM-5.3-Flash","base_model_name":"","max_context_window":1024000,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-09-16"},"id":"nebius/zai-org/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/alia-salamandra:40b","base_model_name":"alia-salamandra:40b","max_context_window":65536,"input_cost":0.3,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":33000,"release_date":"2026-08-19"},"id":"nextbit256/alia-salamandra:40b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.7074,"average_ttft":null,"average_latency":2.493,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.7074,"average_ttft":null,"average_latency":2.493,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/deepseek:v4-flash-0731","base_model_name":"","max_context_window":1048576,"input_cost":0.352,"output_cost":1.056,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"nextbit256/deepseek:v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/deepseek:v4-pro","base_model_name":"","max_context_window":1048576,"input_cost":1.74,"output_cost":3.48,"cache_hit_input_cost":0.145,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-01"},"id":"nextbit256/deepseek:v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/deepseek:v4-pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":1.056,"output_cost":3.168,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-01"},"id":"nextbit256/deepseek:v4-pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/deepseek:v4.1-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.21,"output_cost":0.84,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"nextbit256/deepseek:v4.1-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/euryale:33-70b","base_model_name":"euryale:33-70b","max_context_window":131072,"input_cost":0.65,"output_cost":0.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131000,"release_date":"2024-12-18"},"id":"nextbit256/euryale:33-70b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.2912,"average_ttft":null,"average_latency":0.8143,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.2912,"average_ttft":null,"average_latency":0.8143,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/gemma-2:27b-it","base_model_name":"gemma-2:27b-it","max_context_window":8192,"input_cost":0.65,"output_cost":0.65,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8000,"release_date":"2024-06-27"},"id":"nextbit256/gemma-2:27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/gemma4:26b-a4b","base_model_name":"gemma4:26b-a4b","max_context_window":262144,"input_cost":0.09,"output_cost":0.3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-03-31"},"id":"nextbit256/gemma4:26b-a4b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":44.1078,"average_ttft":0.7587,"average_latency":0.6696,"uptime_percent":100,"cache_hit_percentage":99.584},"throughput":{"average_tps":44.1078,"average_ttft":0.7587,"average_latency":0.6696,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/glm:5.3-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.165,"output_cost":0.55,"cache_hit_input_cost":0.033,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"nextbit256/glm:5.3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/qwen3:14b","base_model_name":"qwen3:14b","max_context_window":40960,"input_cost":0.1,"output_cost":0.22,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":40960,"release_date":"2025-04-29"},"id":"nextbit256/qwen3:14b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":44.3194,"average_ttft":null,"average_latency":2.2586,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":44.3194,"average_ttft":null,"average_latency":2.2586,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Nextbit256","provider_id":"nextbit256","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:53.990816Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.nextbit256.com/v1/models"},"kind":"host","id":"nextbit256"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"nextbit256/remm-slerp:l2-13b","base_model_name":"remm-slerp:l2-13b","max_context_window":6144,"input_cost":0.45,"output_cost":0.65,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":6000},"id":"nextbit256/remm-slerp:l2-13b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.4763,"average_ttft":null,"average_latency":2.5122,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.4763,"average_ttft":null,"average_latency":2.5122,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/baichuan/baichuan-m2-32b","base_model_name":"novita/baichuan/baichuan-m2-32b","max_context_window":131072,"input_cost":0.07,"output_cost":0.07,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13"},"id":"novita/baichuan/baichuan-m2-32b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/baidu/cobuddy","base_model_name":"novita/baidu/cobuddy","max_context_window":131072,"input_cost":0.28,"output_cost":1.13,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-03"},"id":"novita/baidu/cobuddy","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/baidu/ernie-4.5-21B-a3b","base_model_name":"baidu/ernie-4.5-21B-a3b","max_context_window":120000,"input_cost":0.07,"output_cost":0.28,"cache_hit_input_cost":0.007,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-30"},"id":"novita/baidu/ernie-4.5-21B-a3b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/baidu/ernie-4.5-vl-424b-a47b","base_model_name":"baidu/ernie-4.5-vl-424b-a47b","max_context_window":123000,"input_cost":0.42,"output_cost":1.25,"cache_hit_input_cost":0.042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-30"},"id":"novita/baidu/ernie-4.5-vl-424b-a47b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.9037,"average_ttft":null,"average_latency":2.6184,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.9037,"average_ttft":null,"average_latency":2.6184,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/deepseek/deepseek_v3","base_model_name":"deepseek/deepseek_v3","max_context_window":64000,"input_cost":0.89,"output_cost":0.89,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-15"},"id":"novita/deepseek/deepseek_v3","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":14.4924,"average_ttft":null,"average_latency":0.919,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.4924,"average_ttft":null,"average_latency":0.919,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-ocr-2","base_model_name":"novita/deepseek/deepseek-ocr-2","max_context_window":8192,"input_cost":0.03,"output_cost":0.03,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-27"},"id":"novita/deepseek/deepseek-ocr-2","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":53.4911,"average_ttft":null,"average_latency":0.3926,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":53.4911,"average_ttft":null,"average_latency":0.3926,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-r1-0528","base_model_name":"deepseek/deepseek-r1-0528","max_context_window":163840,"input_cost":0.7,"output_cost":2.5,"cache_hit_input_cost":0.35,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek/deepseek-r1-0528"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-05-28","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/deepseek/deepseek-r1-0528","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.7012,"average_ttft":null,"average_latency":5.9141,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.7012,"average_ttft":null,"average_latency":5.9141,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-r1-0528-qwen3-8b","base_model_name":"deepseek/deepseek-r1-0528-qwen3-8b","max_context_window":128000,"input_cost":0.06,"output_cost":0.09,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek/deepseek-r1-0528-qwen3-8b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-05-29","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/deepseek/deepseek-r1-0528-qwen3-8b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-r1-turbo","base_model_name":"deepseek/deepseek-r1-turbo","max_context_window":64000,"input_cost":0.7,"output_cost":2.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek/deepseek-r1-turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":64000,"release_date":"2025-03-05","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/deepseek/deepseek-r1-turbo","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.9993,"average_ttft":null,"average_latency":5.1216,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.9993,"average_ttft":null,"average_latency":5.1216,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/deepseek/deepseek-r1/community","base_model_name":"deepseek/deepseek-r1/community","max_context_window":64000,"input_cost":4,"output_cost":4,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-02-14"},"id":"novita/deepseek/deepseek-r1/community","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.1172,"average_ttft":null,"average_latency":13.3014,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.1172,"average_ttft":null,"average_latency":13.3014,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/deepseek/deepseek-v4-flash","base_model_name":"deepseek/deepseek-v4-flash","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"novita/deepseek/deepseek-v4-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":65.4802,"average_ttft":null,"average_latency":2.6985,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":65.4802,"average_ttft":null,"average_latency":2.6985,"number_of_requests":null},"benchmark":{"cost":0.10023560370265487,"intelligence":0.5331858407079646,"latency":1438.9961937522125,"speed":74.83482068364452,"context":201636.5,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4-flash-0731","base_model_name":"novita/deepseek/deepseek-v4-flash-0731","max_context_window":1048576,"input_cost":0.44,"output_cost":1.32,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-08-01"},"id":"novita/deepseek/deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.6476,"average_ttft":null,"average_latency":1.238,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.6476,"average_ttft":null,"average_latency":1.238,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4-flash-0731-p","base_model_name":"","max_context_window":1048576,"input_cost":0.44,"output_cost":1.32,"cache_hit_input_cost":0.0148,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"novita/deepseek/deepseek-v4-flash-0731-p","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4-flash-vision-exp","base_model_name":"novita/deepseek/deepseek-v4-flash-vision-exp","max_context_window":1048576,"input_cost":0.44,"output_cost":1.32,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-24"},"id":"novita/deepseek/deepseek-v4-flash-vision-exp","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.9201,"average_ttft":null,"average_latency":1.1251,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.9201,"average_ttft":null,"average_latency":1.1251,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/deepseek/deepseek-v4-pro","base_model_name":"deepseek/deepseek-v4-pro","max_context_window":1048576,"input_cost":1.6,"output_cost":3.2,"cache_hit_input_cost":0.135,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24"},"id":"novita/deepseek/deepseek-v4-pro","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.0843,"average_ttft":null,"average_latency":2.2299,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.0843,"average_ttft":null,"average_latency":2.2299,"number_of_requests":null},"benchmark":{"cost":0.24138687892256638,"intelligence":0.6283185840707964,"latency":2212.510104011062,"speed":47.90889675460797,"context":232374.5,"passAt4":0.8849557522123894}},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4-pro-0813","base_model_name":"novita/deepseek/deepseek-v4-pro-0813","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-13"},"id":"novita/deepseek/deepseek-v4-pro-0813","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.407,"average_ttft":null,"average_latency":1.9264,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.407,"average_ttft":null,"average_latency":1.9264,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4-pro-0813-p","base_model_name":"","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"novita/deepseek/deepseek-v4-pro-0813-p","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4.1-flash","base_model_name":"novita/deepseek/deepseek-v4.1-flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"novita/deepseek/deepseek-v4.1-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":67.405,"average_ttft":0.7052,"average_latency":1.5936,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":67.405,"average_ttft":0.7052,"average_latency":1.5936,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4.1-flash-dst","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"novita/deepseek/deepseek-v4.1-flash-dst","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":154.7328,"average_ttft":0.8331,"average_latency":3.6055,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":154.7328,"average_ttft":0.8331,"average_latency":3.6055,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/deepseek/deepseek-v4.1-flash-p","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-24"},"id":"novita/deepseek/deepseek-v4.1-flash-p","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":65.6727,"average_ttft":null,"average_latency":3.4261,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":65.6727,"average_ttft":null,"average_latency":3.4261,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/google/gemma-3-12b-it","base_model_name":"novita/google/gemma-3-12b-it","max_context_window":131072,"input_cost":0.05,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-04"},"id":"novita/google/gemma-3-12b-it","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/google/gemma-3-27b-it","base_model_name":"google/gemma-3-27b-it","max_context_window":98304,"input_cost":0.119,"output_cost":0.2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["google/gemma-3-27b-it"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32000,"release_date":"2025-03-25","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/google/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.9667,"average_ttft":null,"average_latency":1.8707,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.9667,"average_ttft":null,"average_latency":1.8707,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/google/gemma-4-26b-a4b-it","base_model_name":"novita/google/gemma-4-26b-a4b-it","max_context_window":262144,"input_cost":0.13,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"novita/google/gemma-4-26b-a4b-it","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.8993,"average_ttft":null,"average_latency":0.629,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.8993,"average_ttft":null,"average_latency":0.629,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/google/gemma-4-31b-it","base_model_name":"novita/google/gemma-4-31b-it","max_context_window":262144,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"novita/google/gemma-4-31b-it","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.8788,"average_ttft":null,"average_latency":0.8418,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.8788,"average_ttft":null,"average_latency":0.8418,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/gryphe/mythomax-l2-13b","base_model_name":"gryphe/mythomax-l2-13b","max_context_window":4096,"input_cost":0.09,"output_cost":0.09,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gryphe/mythomax-l2-13b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-25"},"id":"novita/gryphe/mythomax-l2-13b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/inclusionai/ling-3.0-flash","base_model_name":"novita/inclusionai/ling-3.0-flash","max_context_window":262144,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-22"},"id":"novita/inclusionai/ling-3.0-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":67.3962,"average_ttft":null,"average_latency":0.86,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":67.3962,"average_ttft":null,"average_latency":0.86,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/inclusionai/ling-3.0-flash-fin","base_model_name":"novita/inclusionai/ling-3.0-flash-fin","max_context_window":262144,"input_cost":0.075,"output_cost":0.22,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-26"},"id":"novita/inclusionai/ling-3.0-flash-fin","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/inclusionai/ling-3.0-flash-sante","base_model_name":"novita/inclusionai/ling-3.0-flash-sante","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-03"},"id":"novita/inclusionai/ling-3.0-flash-sante","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/inclusionai/ling-3.0-flash-vl","base_model_name":"novita/inclusionai/ling-3.0-flash-vl","max_context_window":262144,"input_cost":0.075,"output_cost":0.22,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-03"},"id":"novita/inclusionai/ling-3.0-flash-vl","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/inclusionai/ling-3.1-flash","base_model_name":"novita/inclusionai/ling-3.1-flash","max_context_window":262144,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-28","is_available_on_credits":true},"id":"novita/inclusionai/ling-3.1-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/meta-llama/llama-3.1-8b-instruct","base_model_name":"meta-llama/llama-3.1-8b-instruct","max_context_window":16384,"input_cost":0.02,"output_cost":0.05,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/llama-3.1-8b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16384,"release_date":"2024-07-24","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/meta-llama/llama-3.1-8b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.2762,"average_ttft":null,"average_latency":0.6444,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.2762,"average_ttft":null,"average_latency":0.6444,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/meta-llama/llama-3.2-1b-instruct","base_model_name":"meta-llama/llama-3.2-1b-instruct","max_context_window":131000,"input_cost":0.02,"output_cost":0.02,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/llama-3.2-1b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131000,"release_date":"2024-11-26","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/meta-llama/llama-3.2-1b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/meta-llama/llama-3.3-70b-instruct","base_model_name":"meta-llama/llama-3.3-70b-instruct","max_context_window":12288,"input_cost":0.135,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/llama-3.3-70b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-12-07","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/meta-llama/llama-3.3-70b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.8131,"average_ttft":null,"average_latency":0.6436,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.8131,"average_ttft":null,"average_latency":0.6436,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","base_model_name":"meta-llama/llama-4-maverick-17b-128e-instruct-fp8","max_context_window":1048576,"input_cost":0.27,"output_cost":0.85,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/llama-4-maverick-17b-128e-instruct-fp8"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-04-06","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":43.2594,"average_ttft":null,"average_latency":0.6017,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":43.2594,"average_ttft":null,"average_latency":0.6017,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/meta-llama/llama-4-scout-17b-16e-instruct","base_model_name":"meta-llama/llama-4-scout-17b-16e-instruct","max_context_window":131072,"input_cost":0.18,"output_cost":0.59,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/llama-4-scout-17b-16e-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-04-06","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/meta-llama/llama-4-scout-17b-16e-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.5632,"average_ttft":null,"average_latency":1.276,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.5632,"average_ttft":null,"average_latency":1.276,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/microsoft/wizardlm-2-8x22b","base_model_name":"microsoft/wizardlm-2-8x22b","max_context_window":65535,"input_cost":0.62,"output_cost":0.62,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["microsoft/wizardlm-2-8x22b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":65535,"release_date":"2024-04-24","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/microsoft/wizardlm-2-8x22b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.1763,"average_ttft":null,"average_latency":1.7431,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.1763,"average_ttft":null,"average_latency":1.7431,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/mindai/macaron-v1-tall","base_model_name":"novita/mindai/macaron-v1-tall","max_context_window":262144,"input_cost":0.2475,"output_cost":1.43,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-15"},"id":"novita/mindai/macaron-v1-tall","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.4228,"average_ttft":null,"average_latency":2.0368,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.4228,"average_ttft":null,"average_latency":2.0368,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/mindai/macaron-v1-venti","base_model_name":"novita/mindai/macaron-v1-venti","max_context_window":1048576,"input_cost":0.825,"output_cost":2.475,"cache_hit_input_cost":0.165,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-21"},"id":"novita/mindai/macaron-v1-venti","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.1382,"average_ttft":null,"average_latency":10.4428,"uptime_percent":100,"cache_hit_percentage":87.6712},"throughput":{"average_tps":6.1382,"average_ttft":null,"average_latency":10.4428,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/ming-image-0.1-design","base_model_name":"","max_context_window":0,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-18"},"id":"novita/ming-image-0.1-design","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/ming-image-0.1-design-layer","base_model_name":"","max_context_window":0,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-18"},"id":"novita/ming-image-0.1-design-layer","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m2","base_model_name":"minimax/minimax-m2","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-27"},"id":"novita/minimax/minimax-m2","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.2451,"average_ttft":null,"average_latency":1.9992,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.2451,"average_ttft":null,"average_latency":1.9992,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m2.1","base_model_name":"minimax/minimax-m2.1","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23"},"id":"novita/minimax/minimax-m2.1","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.5926,"average_ttft":null,"average_latency":2.3164,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.5926,"average_ttft":null,"average_latency":2.3164,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m2.5","base_model_name":"minimax/minimax-m2.5","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-12"},"id":"novita/minimax/minimax-m2.5","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.0768,"average_ttft":null,"average_latency":1.6253,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.0768,"average_ttft":null,"average_latency":1.6253,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m2.5-highspeed","base_model_name":"minimax/minimax-m2.5-highspeed","max_context_window":204800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-02"},"id":"novita/minimax/minimax-m2.5-highspeed","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.587,"average_ttft":null,"average_latency":2.2803,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.587,"average_ttft":null,"average_latency":2.2803,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m2.7","base_model_name":"minimax/minimax-m2.7","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-17"},"id":"novita/minimax/minimax-m2.7","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.61,"average_ttft":null,"average_latency":2.6079,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.61,"average_ttft":null,"average_latency":2.6079,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/minimax/minimax-m2.7-highspeed","base_model_name":"novita/minimax/minimax-m2.7-highspeed","max_context_window":204800,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"novita/minimax/minimax-m2.7-highspeed","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.4886,"average_ttft":null,"average_latency":2.6444,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.4886,"average_ttft":null,"average_latency":2.6444,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/minimax/minimax-m3","base_model_name":"minimax/minimax-m3","max_context_window":1000000,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-01"},"id":"novita/minimax/minimax-m3","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.0597,"average_ttft":null,"average_latency":2.1256,"uptime_percent":100,"cache_hit_percentage":72.3164},"throughput":{"average_tps":18.0597,"average_ttft":null,"average_latency":2.1256,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/minimaxai/minimax-m1-80k","base_model_name":"minimaxai/minimax-m1-80k","max_context_window":1000000,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["minimaxai/minimax-m1-80k"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-17"},"id":"novita/minimaxai/minimax-m1-80k","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.8843,"average_ttft":null,"average_latency":2.0838,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.8843,"average_ttft":null,"average_latency":2.0838,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/mistralai/mistral-nemo","base_model_name":"mistralai/mistral-nemo","max_context_window":60288,"input_cost":0.04,"output_cost":0.17,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["mistralai/mistral-nemo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":60288,"release_date":"2024-07-30","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/mistralai/mistral-nemo","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.915,"average_ttft":null,"average_latency":3.0602,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.915,"average_ttft":null,"average_latency":3.0602,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/moonshotai/kimi-k2-0905","base_model_name":"moonshotai/kimi-k2-0905","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-05"},"id":"novita/moonshotai/kimi-k2-0905","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.9921,"average_ttft":null,"average_latency":1.3548,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.9921,"average_ttft":null,"average_latency":1.3548,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/moonshotai/kimi-k2-instruct","base_model_name":"moonshotai/kimi-k2-instruct","max_context_window":131072,"input_cost":0.57,"output_cost":2.3,"cache_hit_input_cost":0.057,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"novita/moonshotai/kimi-k2-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.4954,"average_ttft":null,"average_latency":2.7416,"uptime_percent":100,"cache_hit_percentage":44.4444},"throughput":{"average_tps":11.4954,"average_ttft":null,"average_latency":2.7416,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/moonshotai/kimi-k2-thinking","base_model_name":"moonshotai/kimi-k2-thinking","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-07"},"id":"novita/moonshotai/kimi-k2-thinking","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/moonshotai/kimi-k2.5","base_model_name":"moonshotai/kimi-k2.5","max_context_window":262144,"input_cost":0.6,"output_cost":3,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-27"},"id":"novita/moonshotai/kimi-k2.5","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.1705,"average_ttft":null,"average_latency":1.4022,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.1705,"average_ttft":null,"average_latency":1.4022,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/moonshotai/kimi-k2.6","base_model_name":"moonshotai/kimi-k2.6","max_context_window":262144,"input_cost":0.8,"output_cost":3.4,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-20"},"id":"novita/moonshotai/kimi-k2.6","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":44.2786,"average_ttft":null,"average_latency":16.823,"uptime_percent":100,"cache_hit_percentage":0.0023},"throughput":{"average_tps":44.2786,"average_ttft":null,"average_latency":16.823,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/moonshotai/kimi-k2.7-code","base_model_name":"novita/moonshotai/kimi-k2.7-code","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.19,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"release_date":"2026-06-12"},"id":"novita/moonshotai/kimi-k2.7-code","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.8877,"average_ttft":null,"average_latency":2.593,"uptime_percent":100,"cache_hit_percentage":100},"throughput":{"average_tps":18.8877,"average_ttft":null,"average_latency":2.593,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/moonshotai/kimi-k3","base_model_name":"novita/moonshotai/kimi-k3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16"},"id":"novita/moonshotai/kimi-k3","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.618,"average_ttft":null,"average_latency":4.3822,"uptime_percent":100,"cache_hit_percentage":50},"throughput":{"average_tps":14.618,"average_ttft":null,"average_latency":4.3822,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/moonshotai/kimi-k3-p","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"novita/moonshotai/kimi-k3-p","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/nousresearch/hermes-2-pro-llama-3-8b","base_model_name":"nousresearch/hermes-2-pro-llama-3-8b","max_context_window":8192,"input_cost":0.14,"output_cost":0.14,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["nousresearch/hermes-2-pro-llama-3-8b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8192,"release_date":"2024-06-27","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/nousresearch/hermes-2-pro-llama-3-8b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/nvidia/nemotron-3-nano-30b-a3b","base_model_name":"novita/nvidia/nemotron-3-nano-30b-a3b","max_context_window":262144,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-09"},"id":"novita/nvidia/nemotron-3-nano-30b-a3b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":78.7455,"average_ttft":null,"average_latency":0.4699,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":78.7455,"average_ttft":null,"average_latency":0.4699,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.05,"output_cost":0.25,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-06"},"id":"novita/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":39.3464,"average_ttft":null,"average_latency":1.2395,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":39.3464,"average_ttft":null,"average_latency":1.2395,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.04,"output_cost":0.15,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-06"},"id":"novita/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":46.2942,"average_ttft":null,"average_latency":0.8164,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":46.2942,"average_ttft":null,"average_latency":0.8164,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/paddlepaddle/paddleocr-vl","base_model_name":"novita/paddlepaddle/paddleocr-vl","max_context_window":16384,"input_cost":0.02,"output_cost":0.02,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-22"},"id":"novita/paddlepaddle/paddleocr-vl","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen-2.5-72b-instruct","base_model_name":"qwen/qwen-2.5-72b-instruct","max_context_window":32000,"input_cost":0.38,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["qwen/qwen-2.5-72b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32000,"release_date":"2024-10-15","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/qwen/qwen-2.5-72b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.1306,"average_ttft":null,"average_latency":15.2116,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.1306,"average_ttft":null,"average_latency":15.2116,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen-mt-plus","base_model_name":"novita/qwen/qwen-mt-plus","max_context_window":16384,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-03"},"id":"novita/qwen/qwen-mt-plus","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.3882,"average_ttft":null,"average_latency":0.4913,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.3882,"average_ttft":null,"average_latency":0.4913,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3-235b-a22b-fp8","base_model_name":"qwen/qwen3-235b-a22b-fp8","max_context_window":40960,"input_cost":0.2,"output_cost":0.8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["qwen/qwen3-235b-a22b-fp8"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":40960,"release_date":"2025-04-29","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/qwen/qwen3-235b-a22b-fp8","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.6777,"average_ttft":null,"average_latency":0.9528,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.6777,"average_ttft":null,"average_latency":0.9528,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-235b-a22b-instruct-2507","base_model_name":"qwen/qwen3-235b-a22b-instruct-2507","max_context_window":131072,"input_cost":0.09,"output_cost":0.58,"cache_hit_input_cost":0.009,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-22"},"id":"novita/qwen/qwen3-235b-a22b-instruct-2507","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.4771,"average_ttft":null,"average_latency":0.865,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.4771,"average_ttft":null,"average_latency":0.865,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-235b-a22b-thinking-2507","base_model_name":"qwen/qwen3-235b-a22b-thinking-2507","max_context_window":131072,"input_cost":0.3,"output_cost":3,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-25"},"id":"novita/qwen/qwen3-235b-a22b-thinking-2507","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":53.9521,"average_ttft":null,"average_latency":1.5498,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":53.9521,"average_ttft":null,"average_latency":1.5498,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-coder-30b-a3b-instruct","base_model_name":"qwen/qwen3-coder-30b-a3b-instruct","max_context_window":160000,"input_cost":0.07,"output_cost":0.27,"cache_hit_input_cost":0.007,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-09"},"id":"novita/qwen/qwen3-coder-30b-a3b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.0824,"average_ttft":null,"average_latency":2.7261,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.0824,"average_ttft":null,"average_latency":2.7261,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-coder-480b-a35b-instruct","base_model_name":"qwen/qwen3-coder-480b-a35b-instruct","max_context_window":262144,"input_cost":0.38,"output_cost":1.55,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-23"},"id":"novita/qwen/qwen3-coder-480b-a35b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.783,"average_ttft":null,"average_latency":1.99,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.783,"average_ttft":null,"average_latency":1.99,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-coder-next","base_model_name":"qwen/qwen3-coder-next","max_context_window":262144,"input_cost":0.2,"output_cost":1.5,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-03"},"id":"novita/qwen/qwen3-coder-next","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.4909,"average_ttft":null,"average_latency":1.1944,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.4909,"average_ttft":null,"average_latency":1.1944,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3-max","base_model_name":"novita/qwen/qwen3-max","max_context_window":262144,"input_cost":0.845,"output_cost":3.38,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"novita/qwen/qwen3-max","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.3558,"average_ttft":null,"average_latency":7.5117,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.3558,"average_ttft":null,"average_latency":7.5117,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-next-80b-a3b-instruct","base_model_name":"qwen/qwen3-next-80b-a3b-instruct","max_context_window":131072,"input_cost":0.15,"output_cost":1.5,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-10"},"id":"novita/qwen/qwen3-next-80b-a3b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.9835,"average_ttft":null,"average_latency":1.1524,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.9835,"average_ttft":null,"average_latency":1.1524,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3-omni-30b-a3b-instruct","base_model_name":"","max_context_window":65536,"input_cost":0.25,"output_cost":0.97,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-24"},"id":"novita/qwen/qwen3-omni-30b-a3b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.2192,"average_ttft":null,"average_latency":1.2566,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.2192,"average_ttft":null,"average_latency":1.2566,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3-omni-30b-a3b-thinking","base_model_name":"","max_context_window":65536,"input_cost":0.25,"output_cost":0.97,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-24"},"id":"novita/qwen/qwen3-omni-30b-a3b-thinking","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":37.9399,"average_ttft":null,"average_latency":1.1334,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.9399,"average_ttft":null,"average_latency":1.1334,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-vl-235b-a22b-instruct","base_model_name":"qwen/qwen3-vl-235b-a22b-instruct","max_context_window":131072,"input_cost":0.3,"output_cost":1.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-24"},"id":"novita/qwen/qwen3-vl-235b-a22b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.2705,"average_ttft":null,"average_latency":1.2576,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.2705,"average_ttft":null,"average_latency":1.2576,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-vl-235b-a22b-thinking","base_model_name":"qwen/qwen3-vl-235b-a22b-thinking","max_context_window":131072,"input_cost":0.98,"output_cost":3.95,"cache_hit_input_cost":0.098,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-24"},"id":"novita/qwen/qwen3-vl-235b-a22b-thinking","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.0489,"average_ttft":null,"average_latency":3.2802,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.0489,"average_ttft":null,"average_latency":3.2802,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3-vl-30b-a3b-instruct","base_model_name":"qwen/qwen3-vl-30b-a3b-instruct","max_context_window":131072,"input_cost":0.2,"output_cost":0.7,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-11"},"id":"novita/qwen/qwen3-vl-30b-a3b-instruct","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.3803,"average_ttft":null,"average_latency":0.7258,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.3803,"average_ttft":null,"average_latency":0.7258,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3.5-122b-a10b","base_model_name":"qwen/qwen3.5-122b-a10b","max_context_window":262144,"input_cost":0.4,"output_cost":3.2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"novita/qwen/qwen3.5-122b-a10b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":71.033,"average_ttft":null,"average_latency":5.0544,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":71.033,"average_ttft":null,"average_latency":5.0544,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3.5-27b","base_model_name":"qwen/qwen3.5-27b","max_context_window":262144,"input_cost":0.3,"output_cost":2.4,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"novita/qwen/qwen3.5-27b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":62.0355,"average_ttft":null,"average_latency":5.6455,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":62.0355,"average_ttft":null,"average_latency":5.6455,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.5-35b-a3b","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"novita/qwen/qwen3.5-35b-a3b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":75.1594,"average_ttft":null,"average_latency":6.892,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":75.1594,"average_ttft":null,"average_latency":6.892,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3.5-397b-a17b","base_model_name":"qwen/qwen3.5-397b-a17b","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-16"},"id":"novita/qwen/qwen3.5-397b-a17b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.9045,"average_ttft":null,"average_latency":12.7086,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.9045,"average_ttft":null,"average_latency":12.7086,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.5-plus","base_model_name":"novita/qwen/qwen3.5-plus","max_context_window":1000000,"input_cost":0.4,"output_cost":2.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-16"},"id":"novita/qwen/qwen3.5-plus","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.6-27b","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-23"},"id":"novita/qwen/qwen3.6-27b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":48.088,"average_ttft":null,"average_latency":4.159,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.088,"average_ttft":null,"average_latency":4.159,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.6-35b-a3b","base_model_name":"","max_context_window":262144,"input_cost":0.248,"output_cost":1.485,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-21"},"id":"novita/qwen/qwen3.6-35b-a3b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":83.7949,"average_ttft":null,"average_latency":3.1625,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":83.7949,"average_ttft":null,"average_latency":3.1625,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.6-plus","base_model_name":"novita/qwen/qwen3.6-plus","max_context_window":1000000,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0.625,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-21"},"id":"novita/qwen/qwen3.6-plus","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/qwen/qwen3.7-max","base_model_name":"qwen/qwen3.7-max","max_context_window":1000000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-21"},"id":"novita/qwen/qwen3.7-max","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":49.8827,"average_ttft":null,"average_latency":5.461,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":49.8827,"average_ttft":null,"average_latency":5.461,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.8-2.4t-a95b","base_model_name":"novita/qwen/qwen3.8-2.4t-a95b","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-25"},"id":"novita/qwen/qwen3.8-2.4t-a95b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.5623,"average_ttft":null,"average_latency":2.3487,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.5623,"average_ttft":null,"average_latency":2.3487,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.8-27b","base_model_name":"novita/qwen/qwen3.8-27b","max_context_window":1000000,"input_cost":0.42,"output_cost":3,"cache_hit_input_cost":0.085,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-26"},"id":"novita/qwen/qwen3.8-27b","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.8912,"average_ttft":null,"average_latency":1.3263,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.8912,"average_ttft":null,"average_latency":1.3263,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.8-flash","base_model_name":"novita/qwen/qwen3.8-flash","max_context_window":1000000,"input_cost":0.15,"output_cost":0.47,"cache_hit_input_cost":0.016,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27"},"id":"novita/qwen/qwen3.8-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.2357,"average_ttft":null,"average_latency":2.5996,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.2357,"average_ttft":null,"average_latency":2.5996,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/qwen/qwen3.8-max","base_model_name":"novita/qwen/qwen3.8-max","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-07-31"},"id":"novita/qwen/qwen3.8-max","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.5553,"average_ttft":null,"average_latency":3.0895,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.5553,"average_ttft":null,"average_latency":3.0895,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/sao10k/l3-70b-euryale-v2.1","base_model_name":"sao10k/l3-70b-euryale-v2.1","max_context_window":8192,"input_cost":1.48,"output_cost":1.48,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["sao10k/l3-70b-euryale-v2.1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-06-18"},"id":"novita/sao10k/l3-70b-euryale-v2.1","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/sao10k/l3-8b-lunaris","base_model_name":"sao10k/l3-8b-lunaris","max_context_window":8192,"input_cost":0.05,"output_cost":0.05,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":["sao10k/l3-8b-lunaris"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-08-13"},"id":"novita/sao10k/l3-8b-lunaris","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":39.7247,"average_ttft":null,"average_latency":0.6409,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":39.7247,"average_ttft":null,"average_latency":0.6409,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/Sao10K/L3-8B-Stheno-v3.2","base_model_name":"Sao10K/L3-8B-Stheno-v3.2","max_context_window":8192,"input_cost":0.05,"output_cost":0.05,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Sao10K/L3-8B-Stheno-v3.2"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-11-29"},"id":"novita/Sao10K/L3-8B-Stheno-v3.2","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":33.5491,"average_ttft":null,"average_latency":0.818,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":33.5491,"average_ttft":null,"average_latency":0.818,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/sao10k/l31-70b-euryale-v2.2","base_model_name":"sao10k/l31-70b-euryale-v2.2","max_context_window":8192,"input_cost":1.48,"output_cost":1.48,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["sao10k/l31-70b-euryale-v2.2"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-19"},"id":"novita/sao10k/l31-70b-euryale-v2.2","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.0616,"average_ttft":null,"average_latency":11.0839,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.0616,"average_ttft":null,"average_latency":11.0839,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/stepfun/step-3.7-flash","base_model_name":"novita/stepfun/step-3.7-flash","max_context_window":262144,"input_cost":0.2,"output_cost":1.15,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-12"},"id":"novita/stepfun/step-3.7-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.049,"average_ttft":null,"average_latency":2.3673,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.049,"average_ttft":null,"average_latency":2.3673,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/tencent/hy3","base_model_name":"novita/tencent/hy3","max_context_window":262144,"input_cost":0.14,"output_cost":0.58,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-30"},"id":"novita/tencent/hy3","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.2661,"average_ttft":null,"average_latency":2.5186,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.2661,"average_ttft":null,"average_latency":2.5186,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/tencent/hy4-preview","base_model_name":"novita/tencent/hy4-preview","max_context_window":1000000,"input_cost":0.834,"output_cost":2.501,"cache_hit_input_cost":0.042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-17"},"id":"novita/tencent/hy4-preview","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.4534,"average_ttft":null,"average_latency":7.216,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.4534,"average_ttft":null,"average_latency":7.216,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/thudm/glm-4-32b-0414","base_model_name":"thudm/glm-4-32b-0414","max_context_window":32000,"input_cost":0.55,"output_cost":1.66,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["thudm/glm-4-32b-0414"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32000,"release_date":"2025-04-16","prompt_training":false,"stream_cancellation_supported":true},"id":"novita/thudm/glm-4-32b-0414","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.2278,"average_ttft":null,"average_latency":1.4272,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.2278,"average_ttft":null,"average_latency":1.4272,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/xiaomimimo/mimo-v2.5","base_model_name":"xiaomimimo/mimo-v2.5","max_context_window":1048576,"input_cost":0.168,"output_cost":0.336,"cache_hit_input_cost":0.0034,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-29"},"id":"novita/xiaomimimo/mimo-v2.5","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.4091,"average_ttft":null,"average_latency":3.1374,"uptime_percent":100,"cache_hit_percentage":77.4194},"throughput":{"average_tps":20.4091,"average_ttft":null,"average_latency":3.1374,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/xiaomimimo/mimo-v2.5-pro","base_model_name":"xiaomimimo/mimo-v2.5-pro","max_context_window":1048576,"input_cost":0.522,"output_cost":1.044,"cache_hit_input_cost":0.0043,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-06"},"id":"novita/xiaomimimo/mimo-v2.5-pro","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.9743,"average_ttft":null,"average_latency":3.3739,"uptime_percent":100,"cache_hit_percentage":76.1905},"throughput":{"average_tps":18.9743,"average_ttft":null,"average_latency":3.3739,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/xiaomimimo/mimo-v2.6-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.0028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-24"},"id":"novita/xiaomimimo/mimo-v2.6-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/xiaomimimo/mimo-v2.6-pro","base_model_name":"","max_context_window":1048576,"input_cost":0.435,"output_cost":0.87,"cache_hit_input_cost":0.0036,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-24"},"id":"novita/xiaomimimo/mimo-v2.6-pro","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/autoglm-phone-9b-multilingual","base_model_name":"novita/zai-org/autoglm-phone-9b-multilingual","max_context_window":65536,"input_cost":0.035,"output_cost":0.138,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-10"},"id":"novita/zai-org/autoglm-phone-9b-multilingual","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":68.1696,"average_ttft":null,"average_latency":0.9388,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":68.1696,"average_ttft":null,"average_latency":0.9388,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.5-air","base_model_name":"zai-org/glm-4.5-air","max_context_window":131072,"input_cost":0.13,"output_cost":0.85,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-13"},"id":"novita/zai-org/glm-4.5-air","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":43.8365,"average_ttft":null,"average_latency":1.46,"uptime_percent":100,"cache_hit_percentage":66.6667},"throughput":{"average_tps":43.8365,"average_ttft":null,"average_latency":1.46,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.5v","base_model_name":"zai-org/glm-4.5v","max_context_window":65536,"input_cost":0.6,"output_cost":1.8,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-11"},"id":"novita/zai-org/glm-4.5v","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.5832,"average_ttft":null,"average_latency":2.1622,"uptime_percent":100,"cache_hit_percentage":16.6667},"throughput":{"average_tps":27.5832,"average_ttft":null,"average_latency":2.1622,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.6","base_model_name":"zai-org/glm-4.6","max_context_window":204800,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-30"},"id":"novita/zai-org/glm-4.6","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":34.1795,"average_ttft":null,"average_latency":5.961,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.1795,"average_ttft":null,"average_latency":5.961,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.6v","base_model_name":"zai-org/glm-4.6v","max_context_window":131072,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.055,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-08"},"id":"novita/zai-org/glm-4.6v","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.3144,"average_ttft":null,"average_latency":2.6364,"uptime_percent":100,"cache_hit_percentage":57.1429},"throughput":{"average_tps":25.3144,"average_ttft":null,"average_latency":2.6364,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.7","base_model_name":"zai-org/glm-4.7","max_context_window":204800,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"novita/zai-org/glm-4.7","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":27.0507,"average_ttft":null,"average_latency":58.406,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.0507,"average_ttft":null,"average_latency":58.406,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-4.7-flash","base_model_name":"zai-org/glm-4.7-flash","max_context_window":200000,"input_cost":0.07,"output_cost":0.4,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-19"},"id":"novita/zai-org/glm-4.7-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.8324,"average_ttft":null,"average_latency":11.0504,"uptime_percent":100,"cache_hit_percentage":8.6957},"throughput":{"average_tps":23.8324,"average_ttft":null,"average_latency":11.0504,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-4.7-h","base_model_name":"novita/zai-org/glm-4.7-h","max_context_window":204800,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-26"},"id":"novita/zai-org/glm-4.7-h","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-5","base_model_name":"zai-org/glm-5","max_context_window":202800,"input_cost":1,"output_cost":3.2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-11"},"id":"novita/zai-org/glm-5","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.0999,"average_ttft":null,"average_latency":2.2871,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.0999,"average_ttft":null,"average_latency":2.2871,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5-turbo","base_model_name":"novita/zai-org/glm-5-turbo","max_context_window":202800,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-26"},"id":"novita/zai-org/glm-5-turbo","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.4097,"average_ttft":null,"average_latency":6.2618,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.4097,"average_ttft":null,"average_latency":6.2618,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"novita/zai-org/glm-5.1","base_model_name":"zai-org/glm-5.1","max_context_window":204800,"input_cost":1.38,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"novita/zai-org/glm-5.1","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.4142,"average_ttft":null,"average_latency":2.3042,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.4142,"average_ttft":null,"average_latency":2.3042,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5.2","base_model_name":"novita/zai-org/glm-5.2","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","metadata","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"novita/zai-org/glm-5.2","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":27.156,"average_ttft":null,"average_latency":2.3568,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.156,"average_ttft":null,"average_latency":2.3568,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5.3","base_model_name":"novita/zai-org/glm-5.3","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-19"},"id":"novita/zai-org/glm-5.3","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":34.5544,"average_ttft":null,"average_latency":1.9155,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.5544,"average_ttft":null,"average_latency":1.9155,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5.3-flash","base_model_name":"novita/zai-org/glm-5.3-flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"novita/zai-org/glm-5.3-flash","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.2487,"average_ttft":null,"average_latency":18.1989,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.2487,"average_ttft":null,"average_latency":18.1989,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5.3-p","base_model_name":"novita/zai-org/glm-5.3-p","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"novita/zai-org/glm-5.3-p","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.2546,"average_ttft":null,"average_latency":2.8758,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.2546,"average_ttft":null,"average_latency":2.8758,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Novita","provider_id":"novita","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-12T02:54:19.653440Z","respan_discount_rate":0.1,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.novita.ai/openai/v1/models"},"kind":"host","id":"novita"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"novita/zai-org/glm-5v-turbo","base_model_name":"novita/zai-org/glm-5v-turbo","max_context_window":204800,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"novita/zai-org/glm-5v-turbo","is_byok":false,"effective_discount_rate":0.1,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.6767,"average_ttft":null,"average_latency":2.7059,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.6767,"average_ttft":null,"average_latency":2.7059,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/babbage-002","base_model_name":"openai/babbage-002","max_context_window":16384,"input_cost":0.4,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16384,"release_date":"2023-08-21","prompt_logging":true,"prompt_training":false,"max_output_tokens":16384,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/babbage-002","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/chat-latest","base_model_name":"openai/chat-latest","max_context_window":400000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-05-02","prompt_logging":true,"prompt_training":false,"max_output_tokens":128000,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/chat-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/davinci-002","base_model_name":"openai/davinci-002","max_context_window":16384,"input_cost":2,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16384,"release_date":"2023-08-21","prompt_logging":true,"prompt_training":false,"max_output_tokens":16384,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/davinci-002","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-3.5-turbo","base_model_name":"gpt-3.5-turbo","max_context_window":16385,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-3.5-turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16385,"release_date":"2023-02-28","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-3.5-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":15.5095,"average_ttft":null,"average_latency":1.5205,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.5095,"average_ttft":null,"average_latency":1.5205,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-3.5-turbo-0125","base_model_name":"openai/gpt-3.5-turbo-0125","max_context_window":16385,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16385,"release_date":"2024-01-23","prompt_logging":true,"prompt_training":false,"max_output_tokens":4096,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/gpt-3.5-turbo-0125","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-3.5-turbo-1106","base_model_name":"openai/gpt-3.5-turbo-1106","max_context_window":16385,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16385,"release_date":"2023-11-02","prompt_logging":true,"prompt_training":false,"max_output_tokens":4096,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/gpt-3.5-turbo-1106","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-3.5-turbo-instruct","base_model_name":"openai/gpt-3.5-turbo-instruct","max_context_window":4096,"input_cost":1.5,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4096,"release_date":"2023-08-24","prompt_logging":true,"prompt_training":false,"max_output_tokens":4096,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/gpt-3.5-turbo-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4","base_model_name":"gpt-4","max_context_window":8192,"input_cost":30,"output_cost":60,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8192,"release_date":"2023-06-27","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":4.6445,"average_ttft":null,"average_latency":1.9378,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.6445,"average_ttft":null,"average_latency":1.9378,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4-0613","base_model_name":"gpt-4-0613","max_context_window":8192,"input_cost":30,"output_cost":60,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4-0613"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8192,"release_date":"2023-06-12","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4-0613","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":7.6366,"average_ttft":null,"average_latency":1.1785,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.6366,"average_ttft":null,"average_latency":1.1785,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4-turbo","base_model_name":"gpt-4-turbo","max_context_window":128000,"input_cost":10,"output_cost":30,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-04-05"},"id":"openai/gpt-4-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.2838,"average_ttft":null,"average_latency":1.4323,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.2838,"average_ttft":null,"average_latency":1.4323,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4-turbo-2024-04-09","base_model_name":"gpt-4-turbo-2024-04-09","max_context_window":128000,"input_cost":10,"output_cost":30,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["gpt-4-turbo-2024-04-09"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-04-08","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4-turbo-2024-04-09","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":5.0065,"average_ttft":null,"average_latency":1.7977,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.0065,"average_ttft":null,"average_latency":1.7977,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1","base_model_name":"gpt-4.1","max_context_window":1000000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4.1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":86.5678,"average_ttft":null,"average_latency":0.9893,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":86.5678,"average_ttft":null,"average_latency":0.9893,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1-2025-04-14","base_model_name":"gpt-4.1-2025-04-14","max_context_window":1000000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4.1-2025-04-14"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1-2025-04-14","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":19.3629,"average_ttft":null,"average_latency":0.5295,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.3629,"average_ttft":null,"average_latency":0.5295,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1-mini","base_model_name":"gpt-4.1-mini","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4.1-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":13.1406,"average_ttft":null,"average_latency":0.6027,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.1406,"average_ttft":null,"average_latency":0.6027,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1-mini-2025-04-14","base_model_name":"gpt-4.1-mini-2025-04-14","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4.1-mini-2025-04-14"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1-mini-2025-04-14","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":17.3849,"average_ttft":null,"average_latency":0.52,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.3849,"average_ttft":null,"average_latency":0.52,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1-nano","base_model_name":"gpt-4.1-nano","max_context_window":1000000,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4.1-nano"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":78.7711,"average_ttft":0.8321,"average_latency":1.6498,"uptime_percent":99.9959,"cache_hit_percentage":0.5101},"throughput":{"average_tps":78.7711,"average_ttft":0.8321,"average_latency":1.6498,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4.1-nano-2025-04-14","base_model_name":"openai/gpt-4.1-nano-2025-04-14","max_context_window":1047576,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1047576,"release_date":"2025-04-10","prompt_logging":true,"prompt_training":false,"max_output_tokens":32768,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/gpt-4.1-nano-2025-04-14","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o","base_model_name":"gpt-4o","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-05-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":26.8889,"average_ttft":null,"average_latency":1.0283,"uptime_percent":100,"cache_hit_percentage":6.8687},"throughput":{"average_tps":26.8889,"average_ttft":null,"average_latency":1.0283,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-2024-05-13","base_model_name":"gpt-4o-2024-05-13","max_context_window":128000,"input_cost":5,"output_cost":15,"cache_hit_input_cost":2.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o-2024-05-13"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-05-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-2024-05-13","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":23.3527,"average_ttft":null,"average_latency":0.3854,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3527,"average_ttft":null,"average_latency":0.3854,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-2024-08-06","base_model_name":"gpt-4o-2024-08-06","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o-2024-08-06"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-04","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-2024-08-06","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":62.1796,"average_ttft":29.6442,"average_latency":16.2503,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":62.1796,"average_ttft":29.6442,"average_latency":16.2503,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-2024-11-20","base_model_name":"gpt-4o-2024-11-20","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o-2024-11-20"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-02-12","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-2024-11-20","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":18.0084,"average_ttft":null,"average_latency":0.5553,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.0084,"average_ttft":null,"average_latency":0.5553,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-mini","base_model_name":"gpt-4o-mini","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["gpt-4o-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-16","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":536.9082,"average_ttft":1.1387,"average_latency":2.6589,"uptime_percent":100,"cache_hit_percentage":6.7969},"throughput":{"average_tps":536.9082,"average_ttft":1.1387,"average_latency":2.6589,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-mini-2024-07-18","base_model_name":"gpt-4o-mini-2024-07-18","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o-mini-2024-07-18"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-16","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-mini-2024-07-18","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":17.2465,"average_ttft":null,"average_latency":0.5218,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.2465,"average_ttft":null,"average_latency":0.5218,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-mini-search-preview","base_model_name":"gpt-4o-mini-search-preview","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-4o-mini-search-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-03-07","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-mini-search-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-search-preview","base_model_name":"openai/gpt-4o-search-preview","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2026-02-24","prompt_logging":true,"prompt_training":false,"max_output_tokens":16384,"zero_data_retention":true,"is_available_on_credits":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-search-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-4o-transcribe","base_model_name":"gpt-4o-transcribe","max_context_window":4096,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4096,"release_date":"2025-03-15","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-4o-transcribe","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5","base_model_name":"gpt-5","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":400000,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":301.9785,"average_ttft":1.7297,"average_latency":1.54,"uptime_percent":99.504,"cache_hit_percentage":0},"throughput":{"average_tps":301.9785,"average_ttft":1.7297,"average_latency":1.54,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-2025-08-07","base_model_name":"gpt-5-2025-08-07","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-2025-08-07"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-01","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-2025-08-07","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":52.6218,"average_ttft":null,"average_latency":1.474,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":52.6218,"average_ttft":null,"average_latency":1.474,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-chat-latest","base_model_name":"gpt-5-chat-latest","max_context_window":128000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-chat-latest"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-08-01","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-chat-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-mini","base_model_name":"gpt-5-mini","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":93.3656,"average_ttft":8.6152,"average_latency":7.2693,"uptime_percent":99.8876,"cache_hit_percentage":15.7286},"throughput":{"average_tps":93.3656,"average_ttft":8.6152,"average_latency":7.2693,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-mini-2025-08-07","base_model_name":"gpt-5-mini-2025-08-07","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-mini-2025-08-07"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-mini-2025-08-07","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":283.7489,"average_ttft":9.398,"average_latency":4.6999,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":283.7489,"average_ttft":9.398,"average_latency":4.6999,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-nano","base_model_name":"gpt-5-nano","max_context_window":400000,"input_cost":0.05,"output_cost":0.4,"cache_hit_input_cost":0.005,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-nano"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":139.9098,"average_ttft":null,"average_latency":32.4659,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":139.9098,"average_ttft":null,"average_latency":32.4659,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5-nano-2025-08-07","base_model_name":"gpt-5-nano-2025-08-07","max_context_window":400000,"input_cost":0.05,"output_cost":0.4,"cache_hit_input_cost":0.005,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5-nano-2025-08-07"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5-nano-2025-08-07","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":121.4889,"average_ttft":null,"average_latency":2.7499,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":121.4889,"average_ttft":null,"average_latency":2.7499,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openai/gpt-5-pro","base_model_name":"gpt-5-pro","max_context_window":400000,"input_cost":15,"output_cost":120,"cache_hit_input_cost":1.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"release_date":"2025-10-03"},"id":"openai/gpt-5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":4.3303,"average_ttft":null,"average_latency":14.496,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.3303,"average_ttft":null,"average_latency":14.496,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openai/gpt-5-pro-2025-10-06","base_model_name":"gpt-5-pro-2025-10-06","max_context_window":400000,"input_cost":15,"output_cost":120,"cache_hit_input_cost":1.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-03"},"id":"openai/gpt-5-pro-2025-10-06","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":4.0435,"average_ttft":null,"average_latency":12.1722,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.0435,"average_ttft":null,"average_latency":12.1722,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.1","base_model_name":"gpt-5.1","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5.1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":78.9889,"average_ttft":1.7798,"average_latency":6.8755,"uptime_percent":100,"cache_hit_percentage":3.4718},"throughput":{"average_tps":78.9889,"average_ttft":1.7798,"average_latency":6.8755,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.1-2025-11-13","base_model_name":"gpt-5.1","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.1-2025-11-13","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":30.2329,"average_ttft":null,"average_latency":0.6586,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.2329,"average_ttft":null,"average_latency":0.6586,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.1-codex","base_model_name":"gpt-5.1-codex","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-12","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.1-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.1-codex-max","base_model_name":"gpt-5.1-codex-max","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-20","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.1-codex-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.2","base_model_name":"gpt-5.2","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5.2"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-09","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":71.7943,"average_ttft":null,"average_latency":5.9792,"uptime_percent":100,"cache_hit_percentage":0.4907},"throughput":{"average_tps":71.7943,"average_ttft":null,"average_latency":5.9792,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.2-2025-12-11","base_model_name":"gpt-5.2-2025-12-11","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5.2-2025-12-11"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-09","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.2-2025-12-11","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":19.7045,"average_ttft":null,"average_latency":0.6604,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.7045,"average_ttft":null,"average_latency":0.6604,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.2-codex","base_model_name":"gpt-5.2-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-12-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.2-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.2-pro","base_model_name":"gpt-5.2-pro","max_context_window":400000,"input_cost":21,"output_cost":168,"cache_hit_input_cost":2.1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5.2-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.2-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":2.2843,"average_ttft":null,"average_latency":6.0399,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.2843,"average_ttft":null,"average_latency":6.0399,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.2-pro-2025-12-11","base_model_name":"gpt-5.2-pro-2025-12-11","max_context_window":400000,"input_cost":21,"output_cost":168,"cache_hit_input_cost":2.1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["gpt-5.2-pro-2025-12-11"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.2-pro-2025-12-11","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":2.3799,"average_ttft":null,"average_latency":5.6903,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.3799,"average_ttft":null,"average_latency":5.6903,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.3-codex","base_model_name":"gpt-5.3-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"release_date":"2026-02-08"},"id":"openai/gpt-5.3-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.0106,"average_ttft":null,"average_latency":1.2109,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.0106,"average_ttft":null,"average_latency":1.2109,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4","base_model_name":"gpt-5.4","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-05","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":60.2835,"average_ttft":null,"average_latency":2.531,"uptime_percent":100,"cache_hit_percentage":89.7936},"throughput":{"average_tps":60.2835,"average_ttft":null,"average_latency":2.531,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-2026-03-05","base_model_name":"gpt-5.4-2026-03-05","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-04","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-2026-03-05","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":16.3439,"average_ttft":null,"average_latency":0.6223,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.3439,"average_ttft":null,"average_latency":0.6223,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-mini","base_model_name":"gpt-5.4-mini","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":63.6643,"average_ttft":null,"average_latency":10.1905,"uptime_percent":99.9978,"cache_hit_percentage":39.295},"throughput":{"average_tps":63.6643,"average_ttft":null,"average_latency":10.1905,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-mini-2026-03-17","base_model_name":"gpt-5.4-mini","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-mini-2026-03-17","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":51.7182,"average_ttft":null,"average_latency":1.4017,"uptime_percent":100,"cache_hit_percentage":17.3471},"throughput":{"average_tps":51.7182,"average_ttft":null,"average_latency":1.4017,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-nano","base_model_name":"gpt-5.4-nano","max_context_window":400000,"input_cost":0.2,"output_cost":1.25,"cache_hit_input_cost":0.02,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":57.7351,"average_ttft":null,"average_latency":1.5102,"uptime_percent":99.9994,"cache_hit_percentage":11.2274},"throughput":{"average_tps":57.7351,"average_ttft":null,"average_latency":1.5102,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-nano-2026-03-17","base_model_name":"gpt-5.4-nano","max_context_window":400000,"input_cost":0.2,"output_cost":1.25,"cache_hit_input_cost":0.02,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-nano-2026-03-17","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":26.9062,"average_ttft":null,"average_latency":0.5002,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.9062,"average_ttft":null,"average_latency":0.5002,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-pro","base_model_name":"gpt-5.4-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-04","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":2.8433,"average_ttft":null,"average_latency":3.9908,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.8433,"average_ttft":null,"average_latency":3.9908,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.4-pro-2026-03-05","base_model_name":"gpt-5.4-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-04","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.4-pro-2026-03-05","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":2.9377,"average_ttft":null,"average_latency":3.7493,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.9377,"average_ttft":null,"average_latency":3.7493,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.5","base_model_name":"gpt-5.5","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":1050000,"release_date":"2026-04-22","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":411.0709,"average_ttft":1.8295,"average_latency":2.256,"uptime_percent":100,"cache_hit_percentage":64.7336},"throughput":{"average_tps":411.0709,"average_ttft":1.8295,"average_latency":2.256,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.5-2026-04-23","base_model_name":"openai/gpt-5.5-2026-04-23","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":1050000,"release_date":"2026-04-22","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/gpt-5.5-2026-04-23","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.3319,"average_ttft":null,"average_latency":0.7904,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.3319,"average_ttft":null,"average_latency":0.7904,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openai/gpt-5.5-pro","base_model_name":"gpt-5.5-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"release_date":"2026-04-22"},"id":"openai/gpt-5.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.2456,"average_ttft":null,"average_latency":6.8657,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.2456,"average_ttft":null,"average_latency":6.8657,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openai/gpt-5.5-pro-2026-04-23","base_model_name":"gpt-5.5-pro-2026-04-23","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"openai/gpt-5.5-pro-2026-04-23","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.2144,"average_ttft":null,"average_latency":4.0882,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.2144,"average_ttft":null,"average_latency":4.0882,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.6-luna","base_model_name":"openai/gpt-5.6-luna","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}},"context_size":1050000,"release_date":"2026-06-23"},"id":"openai/gpt-5.6-luna","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":84.9647,"average_ttft":0.9388,"average_latency":5.3722,"uptime_percent":99.9574,"cache_hit_percentage":96.965},"throughput":{"average_tps":84.9647,"average_ttft":0.9388,"average_latency":5.3722,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.6-sol","base_model_name":"openai/gpt-5.6-sol","max_context_window":1050000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.4,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}},"context_size":1050000,"release_date":"2026-06-23"},"id":"openai/gpt-5.6-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":179.2511,"average_ttft":8.1221,"average_latency":10.9696,"uptime_percent":94.4594,"cache_hit_percentage":90.885},"throughput":{"average_tps":179.2511,"average_ttft":8.1221,"average_latency":10.9696,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-5.6-terra","base_model_name":"openai/gpt-5.6-terra","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}},"context_size":1050000,"release_date":"2026-06-23"},"id":"openai/gpt-5.6-terra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":64.1192,"average_ttft":0.842,"average_latency":3.9344,"uptime_percent":98.1627,"cache_hit_percentage":48.3651},"throughput":{"average_tps":64.1192,"average_ttft":0.842,"average_latency":3.9344,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-6-astra","base_model_name":"openai/gpt-6-astra","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":0.2,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7698044042186275,"ci_lo":0.7124964807371247,"model":"gpt-6-astra","config":"mini_swe_agent_gpt_6_astra_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02865396174075141,"harness":"mini-swe-agent","version":"v1.1","n_passed":335,"provider":"openai","ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":335,"pass_at_1":0.7411504424778761,"pass_at_4":0.8053097345132744,"pass_rate":0.7411504424778761,"cost_basis":"Current pricing at all context lengths: $10/M uncached input, $12.50/M cache writes, $1/M cache reads, $50/M output; no separate compute-unit fee.","n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.429117203539823,"n_tasks_in_set":113,"median_cost_usd":3.8406789999999997,"mean_agent_steps":28.754424778761063,"reasoning_effort":"xhigh","mean_cache_tokens":1326921.6836283186,"mean_input_tokens":1456927.0929203539,"n_tasks_attempted":113,"mean_compute_units":752203.0973451327,"mean_output_tokens":29557.327433628318,"median_agent_steps":26,"n_tasks_passed_any":91,"median_input_tokens":1163918.5,"completed_by_attempt":[113,113,113,113],"median_compute_units":662371.5,"median_output_tokens":28542.5,"pass_rate_by_attempt":[0.7079646017699115,0.7345132743362832,0.7787610619469026,0.7433628318584071],"mean_duration_seconds":1132.4004424778761,"mean_reasoning_tokens":11255.66592920354,"mean_cache_read_tokens":1326921.6836283186,"mean_cache_write_tokens":129710.02212389381,"median_duration_seconds":959,"median_reasoning_tokens":10434,"median_cache_read_tokens":1035975,"median_cache_write_tokens":103995,"mean_uncached_input_tokens":295.3871681415929,"median_peak_context_tokens":null,"median_output_tokens_to_pass":28361,"median_uncached_input_tokens":87}},"context_size":1050000,"release_date":"2026-08-27","max_output_tokens":128000,"is_available_on_credits":true},"id":"openai/gpt-6-astra","is_byok":false,"effective_discount_rate":0.2,"response_api_support":true,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":91.9408,"average_ttft":1.8555,"average_latency":15.513,"uptime_percent":85.0942,"cache_hit_percentage":0.3017},"throughput":{"average_tps":91.9408,"average_ttft":1.8555,"average_latency":15.513,"number_of_requests":null},"benchmark":{"cost":4.429117203539823,"intelligence":0.7411504424778761,"latency":1132.4004424778761,"speed":26.101479940216276,"context":null,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-6-luna","base_model_name":"openai/gpt-6-luna","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":0.2,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1050000,"release_date":"2026-09-22","max_output_tokens":128000,"is_available_on_credits":true},"id":"openai/gpt-6-luna","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":128.7139,"average_ttft":1.1028,"average_latency":7.6395,"uptime_percent":99.9819,"cache_hit_percentage":91.0124},"throughput":{"average_tps":128.7139,"average_ttft":1.1028,"average_latency":7.6395,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-6-sol","base_model_name":"openai/gpt-6-sol","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":0.2,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1050000,"release_date":"2026-09-22","max_output_tokens":128000,"is_available_on_credits":true},"id":"openai/gpt-6-sol","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":85.0842,"average_ttft":7.297,"average_latency":9.1285,"uptime_percent":97.1148,"cache_hit_percentage":97.5871},"throughput":{"average_tps":85.0842,"average_ttft":7.297,"average_latency":9.1285,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/gpt-6.1-sol","base_model_name":"openai/gpt-6.1-sol","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":0.2,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"max_input_tokens":922000,"max_output_tokens":128000,"is_available_on_credits":true},"id":"openai/gpt-6.1-sol","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.117,"average_ttft":1.046,"average_latency":1.6942,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.117,"average_ttft":1.046,"average_latency":1.6942,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o1","base_model_name":"o1","max_context_window":200000,"input_cost":15,"output_cost":60,"cache_hit_input_cost":7.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2024-12-16"},"id":"openai/o1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.1788,"average_ttft":null,"average_latency":0.8162,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.1788,"average_ttft":null,"average_latency":0.8162,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o3","base_model_name":"o3","max_context_window":200000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o3"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-09","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":48.1413,"average_ttft":null,"average_latency":0.9209,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.1413,"average_ttft":null,"average_latency":0.9209,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o3-2025-04-16","base_model_name":"o3-2025-04-16","max_context_window":200000,"input_cost":10,"output_cost":40,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o3-2025-04-16"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-08","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o3-2025-04-16","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":36.302,"average_ttft":null,"average_latency":0.7456,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.302,"average_ttft":null,"average_latency":0.7456,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o3-mini","base_model_name":"o3-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.55,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o3-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-01-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o3-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":91.6677,"average_ttft":null,"average_latency":1.2766,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":91.6677,"average_ttft":null,"average_latency":1.2766,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o3-mini-2025-01-31","base_model_name":"o3-mini-2025-01-31","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.55,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o3-mini-2025-01-31"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-01-27","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o3-mini-2025-01-31","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":50.2115,"average_ttft":null,"average_latency":1.0684,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":50.2115,"average_ttft":null,"average_latency":1.0684,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o4-mini","base_model_name":"o4-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o4-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-09","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o4-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":36.8514,"average_ttft":null,"average_latency":0.7466,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.8514,"average_ttft":null,"average_latency":0.7466,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/o4-mini-2025-04-16","base_model_name":"o4-mini-2025-04-16","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["o4-mini-2025-04-16"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-08","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/o4-mini-2025-04-16","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":67.3346,"average_ttft":null,"average_latency":0.8205,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":67.3346,"average_ttft":null,"average_latency":0.8205,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/text-embedding-3-large","base_model_name":"text-embedding-3-large","max_context_window":8191,"input_cost":0.13,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8191,"release_date":"2024-01-22","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/text-embedding-3-large","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/text-embedding-3-small","base_model_name":"text-embedding-3-small","max_context_window":8191,"input_cost":0.02,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8191,"release_date":"2024-01-22","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/text-embedding-3-small","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/text-embedding-ada-002","base_model_name":"text-embedding-ada-002","max_context_window":8191,"input_cost":0.1,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"embedding","metadata":{"context_size":8191,"release_date":"2022-12-16","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/text-embedding-ada-002","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/tts-1","base_model_name":"tts-1","max_context_window":4096,"input_cost":0,"output_cost":0.015,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4096,"release_date":"2023-04-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/tts-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenAI","provider_id":"openai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.436496Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.openai.com/v1/models"},"kind":"host","id":"openai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openai/whisper-1","base_model_name":"whisper-1","max_context_window":4096,"input_cost":0.006,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4096,"release_date":"2023-02-27","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openai/whisper-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~anthropic/claude-fable-latest","base_model_name":"","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0.25,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-09"},"id":"openrouter/~anthropic/claude-fable-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":4.1819,"average_ttft":null,"average_latency":3.2307,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.1819,"average_ttft":null,"average_latency":3.2307,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~anthropic/claude-haiku-latest","base_model_name":"","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/~anthropic/claude-haiku-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.3136,"average_ttft":null,"average_latency":0.7299,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3136,"average_ttft":null,"average_latency":0.7299,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~anthropic/claude-opus-latest","base_model_name":"","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-21","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/~anthropic/claude-opus-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.2656,"average_ttft":null,"average_latency":3.427,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.2656,"average_ttft":null,"average_latency":3.427,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~anthropic/claude-sonnet-latest","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/~anthropic/claude-sonnet-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":66.8387,"average_ttft":6.2619,"average_latency":7.0222,"uptime_percent":50,"cache_hit_percentage":0},"throughput":{"average_tps":66.8387,"average_ttft":6.2619,"average_latency":7.0222,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~deepseek/deepseek-flash-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.0244,"output_cost":0.6,"cache_hit_input_cost":0.0244,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-14"},"id":"openrouter/~deepseek/deepseek-flash-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.4515,"average_ttft":null,"average_latency":2.0175,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.4515,"average_ttft":null,"average_latency":2.0175,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~deepseek/deepseek-pro-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.217,"output_cost":3.5,"cache_hit_input_cost":0.217,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-14"},"id":"openrouter/~deepseek/deepseek-pro-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.9593,"average_ttft":null,"average_latency":2.0417,"uptime_percent":100,"cache_hit_percentage":4.4944},"throughput":{"average_tps":12.9593,"average_ttft":null,"average_latency":2.0417,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~deepseek/deepseek-v4-flash-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.0108,"output_cost":1.28,"cache_hit_input_cost":0.0108,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-08-01"},"id":"openrouter/~deepseek/deepseek-v4-flash-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":128.6236,"average_ttft":2.6876,"average_latency":10.5401,"uptime_percent":100,"cache_hit_percentage":53.1258},"throughput":{"average_tps":128.6236,"average_ttft":2.6876,"average_latency":10.5401,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~google/gemini-flash-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"openrouter/~google/gemini-flash-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.9102,"average_ttft":null,"average_latency":1.6921,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.9102,"average_ttft":null,"average_latency":1.6921,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~google/gemini-pro-latest","base_model_name":"","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/~google/gemini-pro-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":28.8447,"average_ttft":null,"average_latency":2.0868,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.8447,"average_ttft":null,"average_latency":2.0868,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~moonshotai/kimi-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.7264,"output_cost":10,"cache_hit_input_cost":0.7264,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"openrouter/~moonshotai/kimi-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.4026,"average_ttft":null,"average_latency":2.441,"uptime_percent":100,"cache_hit_percentage":58.1395},"throughput":{"average_tps":27.4026,"average_ttft":null,"average_latency":2.441,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~openai/gpt-astra-latest","base_model_name":"","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/~openai/gpt-astra-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.4148,"average_ttft":null,"average_latency":1.755,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.4148,"average_ttft":null,"average_latency":1.755,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~openai/gpt-luna-latest","base_model_name":"","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/~openai/gpt-luna-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.1131,"average_ttft":null,"average_latency":0.8742,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.1131,"average_ttft":null,"average_latency":0.8742,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~openai/gpt-mini-latest","base_model_name":"","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-27"},"id":"openrouter/~openai/gpt-mini-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.344,"average_ttft":null,"average_latency":0.5693,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.344,"average_ttft":null,"average_latency":0.5693,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~openai/gpt-sol-latest","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/~openai/gpt-sol-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.597,"average_ttft":null,"average_latency":1.1485,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.597,"average_ttft":null,"average_latency":1.1485,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~openai/gpt-terra-latest","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/~openai/gpt-terra-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.3642,"average_ttft":null,"average_latency":0.8474,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.3642,"average_ttft":null,"average_latency":0.8474,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~x-ai/grok-latest","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-08"},"id":"openrouter/~x-ai/grok-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":44.8214,"average_ttft":null,"average_latency":2.3112,"uptime_percent":100,"cache_hit_percentage":61.8357},"throughput":{"average_tps":44.8214,"average_ttft":null,"average_latency":2.3112,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~z-ai/glm-flash-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.02,"output_cost":0.3,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27"},"id":"openrouter/~z-ai/glm-flash-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.3641,"average_ttft":null,"average_latency":2.3333,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.3641,"average_ttft":null,"average_latency":2.3333,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/~z-ai/glm-latest","base_model_name":"","max_context_window":1048576,"input_cost":0.06,"output_cost":2.694,"cache_hit_input_cost":0.176,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-19"},"id":"openrouter/~z-ai/glm-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":92.1273,"average_ttft":null,"average_latency":0.6949,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":92.1273,"average_ttft":null,"average_latency":0.6949,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-2.0","base_model_name":"","max_context_window":131072,"input_cost":0.7999999999999999,"output_cost":1.5999999999999999,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-23"},"id":"openrouter/aion-labs/aion-2.0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":34.4615,"average_ttft":null,"average_latency":1.7932,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.4615,"average_ttft":null,"average_latency":1.7932,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-3.0","base_model_name":"","max_context_window":131072,"input_cost":3,"output_cost":6,"cache_hit_input_cost":0.75,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-07"},"id":"openrouter/aion-labs/aion-3.0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.0057,"average_ttft":null,"average_latency":1.7524,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.0057,"average_ttft":null,"average_latency":1.7524,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-3.0-mini","base_model_name":"","max_context_window":131072,"input_cost":0.7,"output_cost":1.4,"cache_hit_input_cost":0.18,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-07"},"id":"openrouter/aion-labs/aion-3.0-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":42.2794,"average_ttft":null,"average_latency":1.5137,"uptime_percent":100,"cache_hit_percentage":100},"throughput":{"average_tps":42.2794,"average_ttft":null,"average_latency":1.5137,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-3.5","base_model_name":"","max_context_window":262144,"input_cost":3,"output_cost":6,"cache_hit_input_cost":0.75,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"openrouter/aion-labs/aion-3.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-3.5-mini","base_model_name":"","max_context_window":262144,"input_cost":0.7,"output_cost":1.4,"cache_hit_input_cost":0.18,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"openrouter/aion-labs/aion-3.5-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/aion-labs/aion-rp-llama-3.1-8b","base_model_name":"","max_context_window":32768,"input_cost":0.7999999999999999,"output_cost":1.5999999999999999,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32768,"release_date":"2025-02-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/aion-labs/aion-rp-llama-3.1-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.6886,"average_ttft":null,"average_latency":1.7582,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.6886,"average_ttft":null,"average_latency":1.7582,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/amazon/nova-2-lite-v1","base_model_name":"","max_context_window":1000000,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-12-02","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/amazon/nova-2-lite-v1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.8883,"average_ttft":null,"average_latency":0.6388,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.8883,"average_ttft":null,"average_latency":0.6388,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/amazon/nova-lite-v1","base_model_name":"","max_context_window":300000,"input_cost":0.06,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/amazon/nova-lite-v1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":300000,"release_date":"2024-12-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/amazon/nova-lite-v1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":87.9631,"average_ttft":null,"average_latency":0.588,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":87.9631,"average_ttft":null,"average_latency":0.588,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/amazon/nova-micro-v1","base_model_name":"","max_context_window":128000,"input_cost":0.035,"output_cost":0.14,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-12-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/amazon/nova-micro-v1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":105.6385,"average_ttft":null,"average_latency":0.3883,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":105.6385,"average_ttft":null,"average_latency":0.3883,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/amazon/nova-premier-v1","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-10-31","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/amazon/nova-premier-v1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":46.496,"average_ttft":null,"average_latency":1.3765,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":46.496,"average_ttft":null,"average_latency":1.3765,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/amazon/nova-pro-v1","base_model_name":"","max_context_window":300000,"input_cost":0.7999999999999999,"output_cost":3.1999999999999997,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/amazon/nova-pro-v1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":300000,"release_date":"2024-12-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/amazon/nova-pro-v1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":73.5441,"average_ttft":null,"average_latency":0.824,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":73.5441,"average_ttft":null,"average_latency":0.824,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthracite-org/magnum-v4-72b","base_model_name":"","max_context_window":32768,"input_cost":2.5,"output_cost":5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-22"},"id":"openrouter/anthracite-org/magnum-v4-72b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.8824,"average_ttft":null,"average_latency":2.3814,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.8824,"average_ttft":null,"average_latency":2.3814,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-fable-5","base_model_name":"openrouter/anthropic/claude-fable-5","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}},"release_date":"2026-06-09"},"id":"openrouter/anthropic/claude-fable-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.4808,"average_ttft":null,"average_latency":4.1369,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.4808,"average_ttft":null,"average_latency":4.1369,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-fable-5:batch","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-09"},"id":"openrouter/anthropic/claude-fable-5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-fable-5.1","base_model_name":"","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0.25,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-01"},"id":"openrouter/anthropic/claude-fable-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":2.8307,"average_ttft":null,"average_latency":7.4947,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.8307,"average_ttft":null,"average_latency":7.4947,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-fable-5.1:batch","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.125,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-01"},"id":"openrouter/anthropic/claude-fable-5.1:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-haiku-4.5","base_model_name":"openrouter/anthropic/claude-haiku-4.5","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.09999999999999999,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-15"},"id":"openrouter/anthropic/claude-haiku-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":58.766,"average_ttft":0.9764,"average_latency":0.9742,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":58.766,"average_ttft":0.9764,"average_latency":0.9742,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-haiku-4.5:batch","base_model_name":"","max_context_window":200000,"input_cost":0.5,"output_cost":2.5,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0.625,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-15"},"id":"openrouter/anthropic/claude-haiku-4.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.1","base_model_name":"openrouter/anthropic/claude-opus-4.1","max_context_window":200000,"input_cost":15,"output_cost":75,"cache_hit_input_cost":1.5,"cache_creation_input_cost":18.75,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-opus-4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.0087,"average_ttft":null,"average_latency":4.1238,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.0087,"average_ttft":null,"average_latency":4.1238,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.1:batch","base_model_name":"","max_context_window":200000,"input_cost":7.5,"output_cost":37.5,"cache_hit_input_cost":0.75,"cache_creation_input_cost":9.375,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"openrouter/anthropic/claude-opus-4.1:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.5","base_model_name":"openrouter/anthropic/claude-opus-4.5","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-11-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-opus-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.8454,"average_ttft":null,"average_latency":1.6595,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.8454,"average_ttft":null,"average_latency":1.6595,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.5:batch","base_model_name":"","max_context_window":200000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":3.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-24"},"id":"openrouter/anthropic/claude-opus-4.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.6","base_model_name":"openrouter/anthropic/claude-opus-4.6","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-02-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-opus-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.0098,"average_ttft":null,"average_latency":1.8457,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.0098,"average_ttft":null,"average_latency":1.8457,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.6:batch","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":3.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-04"},"id":"openrouter/anthropic/claude-opus-4.6:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.7","base_model_name":"openrouter/anthropic/claude-opus-4.7","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-opus-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.2371,"average_ttft":null,"average_latency":1.0513,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.2371,"average_ttft":null,"average_latency":1.0513,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.7:batch","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":3.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"openrouter/anthropic/claude-opus-4.7:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openrouter/anthropic/claude-opus-4.8","base_model_name":"anthropic/claude-opus-4.8","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}},"release_date":"2026-05-27"},"id":"openrouter/anthropic/claude-opus-4.8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.694,"average_ttft":null,"average_latency":1.2236,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.694,"average_ttft":null,"average_latency":1.2236,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-4.8:batch","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":3.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-27"},"id":"openrouter/anthropic/claude-opus-4.8:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-5","base_model_name":"openrouter/anthropic/claude-opus-5","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7752095907502038,"ci_lo":0.6977633822227692,"model":"claude-opus-5","config":"mini_swe_agent_claude_opus_5_max","n_runs":4,"source":"deep-swe","ci_half":0.03872310426371729,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7364864864864865,"pass_at_4":0.8849557522123894,"pass_rate":0.7364864864864865,"n_attempted":444,"ci_attempted":444,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":11.837583271396396,"n_tasks_in_set":113,"median_cost_usd":10.4281505,"mean_agent_steps":99.0427927927928,"reasoning_effort":"max","mean_cache_tokens":14784785.963963963,"mean_input_tokens":15025834.39864865,"n_tasks_attempted":113,"mean_output_tokens":117565.6936936937,"median_agent_steps":90.5,"n_tasks_passed_any":100,"median_input_tokens":12130307.5,"median_output_tokens":113366.5,"mean_duration_seconds":1911.819866231982,"median_duration_seconds":1801.1237265,"median_peak_context_tokens":215810,"median_output_tokens_to_pass":112874}},"release_date":"2026-07-24"},"id":"openrouter/anthropic/claude-opus-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.2774,"average_ttft":null,"average_latency":3.5723,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.2774,"average_ttft":null,"average_latency":3.5723,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-5:batch","base_model_name":"","max_context_window":1000000,"input_cost":2.5,"output_cost":12.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":3.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-24"},"id":"openrouter/anthropic/claude-opus-5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-5.5","base_model_name":"","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/anthropic/claude-opus-5.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-opus-5.5:batch","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/anthropic/claude-opus-5.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-4","base_model_name":"openrouter/anthropic/claude-sonnet-4","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}},"context_size":1000000,"release_date":"2025-05-22","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-sonnet-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":24.523,"average_ttft":null,"average_latency":0.8162,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.523,"average_ttft":null,"average_latency":0.8162,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-4.5","base_model_name":"openrouter/anthropic/claude-sonnet-4.5","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"context_size":1000000,"release_date":"2025-09-29","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-sonnet-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.5539,"average_ttft":null,"average_latency":1.8807,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.5539,"average_ttft":null,"average_latency":1.8807,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-4.5:batch","base_model_name":"","max_context_window":1000000,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":1.875,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-29"},"id":"openrouter/anthropic/claude-sonnet-4.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-4.6","base_model_name":"openrouter/anthropic/claude-sonnet-4.6","max_context_window":1000000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}},"context_size":1000000,"release_date":"2026-02-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/anthropic/claude-sonnet-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.1882,"average_ttft":null,"average_latency":1.3266,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.1882,"average_ttft":null,"average_latency":1.3266,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-4.6:batch","base_model_name":"","max_context_window":1000000,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":1.875,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-17"},"id":"openrouter/anthropic/claude-sonnet-4.6:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-5","base_model_name":"openrouter/anthropic/claude-sonnet-5","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"release_date":"2026-06-30"},"id":"openrouter/anthropic/claude-sonnet-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":174.4095,"average_ttft":2.2577,"average_latency":4.4048,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":174.4095,"average_ttft":2.2577,"average_latency":4.4048,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-5:batch","base_model_name":"","max_context_window":1000000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-30"},"id":"openrouter/anthropic/claude-sonnet-5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-5.5","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"openrouter/anthropic/claude-sonnet-5.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/anthropic/claude-sonnet-5.5:batch","base_model_name":"openrouter/anthropic/claude-sonnet-5.5:batch","max_context_window":1000000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","input_cost","max_context_window","metadata","model_type","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-09-28","is_available_on_credits":true},"id":"openrouter/anthropic/claude-sonnet-5.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/arcee-ai/trinity-large-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":0.7999999999999999,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-01"},"id":"openrouter/arcee-ai/trinity-large-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":117.997,"average_ttft":null,"average_latency":0.5732,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":117.997,"average_ttft":null,"average_latency":0.5732,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/baidu/ernie-4.5-vl-424b-a47b","base_model_name":"","max_context_window":123000,"input_cost":0.42,"output_cost":1.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-30","expiration_date":"2026-10-08"},"id":"openrouter/baidu/ernie-4.5-vl-424b-a47b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.1536,"average_ttft":null,"average_latency":2.3334,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.1536,"average_ttft":null,"average_latency":2.3334,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-1.6","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23","expiration_date":"2026-11-11"},"id":"openrouter/bytedance-seed/seed-1.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.0201,"average_ttft":null,"average_latency":2.1433,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.0201,"average_ttft":null,"average_latency":2.1433,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-1.6-flash","base_model_name":"","max_context_window":262144,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23","expiration_date":"2026-11-11"},"id":"openrouter/bytedance-seed/seed-1.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":63.9914,"average_ttft":null,"average_latency":0.9759,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":63.9914,"average_ttft":null,"average_latency":0.9759,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-2-1-turbo","base_model_name":"","max_context_window":262144,"input_cost":0.5,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-12"},"id":"openrouter/bytedance-seed/seed-2-1-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.7301,"average_ttft":null,"average_latency":2.8166,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.7301,"average_ttft":null,"average_latency":2.8166,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-2.0-code","base_model_name":"","max_context_window":262144,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-12","expiration_date":"2026-11-11"},"id":"openrouter/bytedance-seed/seed-2.0-code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.0839,"average_ttft":null,"average_latency":1.5279,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.0839,"average_ttft":null,"average_latency":1.5279,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-2.0-lite","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-10"},"id":"openrouter/bytedance-seed/seed-2.0-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":31.5592,"average_ttft":null,"average_latency":2.3341,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.5592,"average_ttft":null,"average_latency":2.3341,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance-seed/seed-2.0-mini","base_model_name":"","max_context_window":262144,"input_cost":0.09999999999999999,"output_cost":0.39999999999999997,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"openrouter/bytedance-seed/seed-2.0-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":59.8383,"average_ttft":null,"average_latency":1.0902,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":59.8383,"average_ttft":null,"average_latency":1.0902,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/bytedance/ui-tars-1.5-7b","base_model_name":"","max_context_window":128000,"input_cost":0.09999999999999999,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-22"},"id":"openrouter/bytedance/ui-tars-1.5-7b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.0075,"average_ttft":null,"average_latency":0.5536,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.0075,"average_ttft":null,"average_latency":0.5536,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition","base_model_name":"","max_context_window":128000,"input_cost":0.19999999999999998,"output_cost":0.8999999999999999,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-09"},"id":"openrouter/cognitivecomputations/dolphin-mistral-24b-venice-edition","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.6073,"average_ttft":null,"average_latency":0.5425,"uptime_percent":100,"cache_hit_percentage":97.491},"throughput":{"average_tps":18.6073,"average_ttft":null,"average_latency":0.5425,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cohere/command-a","base_model_name":"openrouter/cohere/command-a","max_context_window":256000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":256000,"release_date":"2025-03-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/cohere/command-a","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.964,"average_ttft":null,"average_latency":0.6963,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.964,"average_ttft":null,"average_latency":0.6963,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cohere/command-a-plus","base_model_name":"","max_context_window":192000,"input_cost":0.3,"output_cost":1.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/cohere/command-a-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cohere/command-r-08-2024","base_model_name":"openrouter/cohere/command-r-08-2024","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-30","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/cohere/command-r-08-2024","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.622,"average_ttft":null,"average_latency":10.0206,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.622,"average_ttft":null,"average_latency":10.0206,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cohere/command-r-plus-08-2024","base_model_name":"openrouter/cohere/command-r-plus-08-2024","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-30","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/cohere/command-r-plus-08-2024","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.1496,"average_ttft":null,"average_latency":1.1854,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.1496,"average_ttft":null,"average_latency":1.1854,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/cohere/command-r7b-12-2024","base_model_name":"openrouter/cohere/command-r7b-12-2024","max_context_window":128000,"input_cost":0.0375,"output_cost":0.15,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-12-14","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/cohere/command-r7b-12-2024","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.0053,"average_ttft":null,"average_latency":0.4944,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.0053,"average_ttft":null,"average_latency":0.4944,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-chat","base_model_name":"","max_context_window":163840,"input_cost":0.2574,"output_cost":1.0287,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/deepseek/deepseek-chat"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-12-26","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-chat","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.7371,"average_ttft":null,"average_latency":2.6366,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.7371,"average_ttft":null,"average_latency":2.6366,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-chat-v3-0324","base_model_name":"","max_context_window":163840,"input_cost":0.29,"output_cost":1.14,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-03-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-chat-v3-0324","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.3194,"average_ttft":null,"average_latency":2.9772,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.3194,"average_ttft":null,"average_latency":2.9772,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-chat-v3.1","base_model_name":"","max_context_window":163840,"input_cost":0.25,"output_cost":0.95,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-08-21","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-chat-v3.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.7294,"average_ttft":null,"average_latency":2.4275,"uptime_percent":100,"cache_hit_percentage":15.3846},"throughput":{"average_tps":15.7294,"average_ttft":null,"average_latency":2.4275,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-r1","base_model_name":"","max_context_window":64000,"input_cost":0.7,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-01-20","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-r1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.3025,"average_ttft":1.2063,"average_latency":13.8902,"uptime_percent":100,"cache_hit_percentage":39.9301},"throughput":{"average_tps":15.3025,"average_ttft":1.2063,"average_latency":13.8902,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-r1-0528","base_model_name":"","max_context_window":163840,"input_cost":0.5,"output_cost":2.1500000000000004,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-05-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-r1-0528","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.7669,"average_ttft":null,"average_latency":13.3551,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.7669,"average_ttft":null,"average_latency":13.3551,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v3.1-terminus","base_model_name":"","max_context_window":163840,"input_cost":0.3,"output_cost":1,"cache_hit_input_cost":0.135,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-09-22","prompt_logging":false,"expiration_date":"2026-09-28","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-v3.1-terminus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.4445,"average_ttft":null,"average_latency":3.3226,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.4445,"average_ttft":null,"average_latency":3.3226,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v3.2","base_model_name":"","max_context_window":163840,"input_cost":0.28,"output_cost":0.42,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":131072,"release_date":"2025-12-01","prompt_logging":false,"expiration_date":"2026-09-28","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-v3.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.9153,"average_ttft":null,"average_latency":2.0382,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.9153,"average_ttft":null,"average_latency":2.0382,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v3.2-exp","base_model_name":"","max_context_window":163840,"input_cost":0.27,"output_cost":0.41,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":163840,"release_date":"2025-09-29","prompt_logging":false,"expiration_date":"2026-09-28","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-v3.2-exp","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.9314,"average_ttft":null,"average_latency":10.1634,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.9314,"average_ttft":null,"average_latency":10.1634,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.042,"output_cost":0.084,"cache_hit_input_cost":0.0084,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"context_size":1048576,"release_date":"2026-04-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-v4-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":36.1175,"average_ttft":null,"average_latency":1.9569,"uptime_percent":100,"cache_hit_percentage":50},"throughput":{"average_tps":36.1175,"average_ttft":null,"average_latency":1.9569,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4-flash-0731","base_model_name":"","max_context_window":1048576,"input_cost":0.0108,"output_cost":1.28,"cache_hit_input_cost":0.0108,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-31"},"id":"openrouter/deepseek/deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":45.5985,"average_ttft":null,"average_latency":8.7744,"uptime_percent":99.9963,"cache_hit_percentage":52.4377},"throughput":{"average_tps":45.5985,"average_ttft":null,"average_latency":8.7744,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4-flash-vision-exp","base_model_name":"","max_context_window":1048576,"input_cost":0.2156,"output_cost":0.6468,"cache_hit_input_cost":0.00686,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-21"},"id":"openrouter/deepseek/deepseek-v4-flash-vision-exp","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":67.3976,"average_ttft":2.5384,"average_latency":8.096,"uptime_percent":100,"cache_hit_percentage":26.2697},"throughput":{"average_tps":67.3976,"average_ttft":2.5384,"average_latency":8.096,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4-pro","base_model_name":"","max_context_window":1048576,"input_cost":0.2088,"output_cost":0.4176,"cache_hit_input_cost":0.0174,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"context_size":1048576,"release_date":"2026-04-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/deepseek/deepseek-v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":50.3924,"average_ttft":null,"average_latency":15.7418,"uptime_percent":100,"cache_hit_percentage":72.8054},"throughput":{"average_tps":50.3924,"average_ttft":null,"average_latency":15.7418,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4-pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":0.66,"output_cost":1.98,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-12"},"id":"openrouter/deepseek/deepseek-v4-pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":41.592,"average_ttft":null,"average_latency":10.6754,"uptime_percent":100,"cache_hit_percentage":88.8584},"throughput":{"average_tps":41.592,"average_ttft":null,"average_latency":10.6754,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4.1-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.03,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"openrouter/deepseek/deepseek-v4.1-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":173.4919,"average_ttft":1.905,"average_latency":14.5666,"uptime_percent":99.3396,"cache_hit_percentage":89.9154},"throughput":{"average_tps":173.4919,"average_ttft":1.905,"average_latency":14.5666,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/deepseek/deepseek-v4.1-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.112,"output_cost":0.336,"cache_hit_input_cost":0.00336,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"openrouter/deepseek/deepseek-v4.1-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/fireworks/ember-1","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-24"},"id":"openrouter/fireworks/ember-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-flash","base_model_name":"openrouter/google/gemini-2.5-flash","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0.08333333333333334,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2025-06-17","prompt_logging":false,"expiration_date":"2026-10-20","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-2.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.5701,"average_ttft":null,"average_latency":2.3184,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.5701,"average_ttft":null,"average_latency":2.3184,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-flash-image","base_model_name":"","max_context_window":32768,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0.0833333333333333,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-07","expiration_date":"2027-03-15"},"id":"openrouter/google/gemini-2.5-flash-image","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":37.7942,"average_ttft":null,"average_latency":0.5733,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.7942,"average_ttft":null,"average_latency":0.5733,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-flash-lite","base_model_name":"openrouter/google/gemini-2.5-flash-lite","max_context_window":1048576,"input_cost":0.09999999999999999,"output_cost":0.39999999999999997,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.0833333333333333,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/google/gemini-2.5-flash-lite"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-07-22","prompt_logging":false,"expiration_date":"2026-10-20","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-2.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.0587,"average_ttft":null,"average_latency":0.3197,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.0587,"average_ttft":null,"average_latency":0.3197,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-flash-lite:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.049999999999999996,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-22"},"id":"openrouter/google/gemini-2.5-flash-lite:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":1.25,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-17","expiration_date":"2026-10-20"},"id":"openrouter/google/gemini-2.5-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-pro","base_model_name":"openrouter/google/gemini-2.5-pro","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-06-17","prompt_logging":false,"expiration_date":"2026-10-20","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":38.0155,"average_ttft":null,"average_latency":1.5684,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.0155,"average_ttft":null,"average_latency":1.5684,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-pro-preview","base_model_name":"openrouter/google/gemini-2.5-pro-preview","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-06-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-2.5-pro-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.5471,"average_ttft":null,"average_latency":1.9315,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.5471,"average_ttft":null,"average_latency":1.9315,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-2.5-pro:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.625,"output_cost":5,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-17","expiration_date":"2026-10-20"},"id":"openrouter/google/gemini-2.5-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3-flash-preview","base_model_name":"openrouter/google/gemini-3-flash-preview","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.049999999999999996,"cache_creation_input_cost":0.08333333333333334,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-12-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-3-flash-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.9286,"average_ttft":null,"average_latency":2.1033,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.9286,"average_ttft":null,"average_latency":2.1033,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3-flash-preview:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-17"},"id":"openrouter/google/gemini-3-flash-preview:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3-pro-image","base_model_name":"","max_context_window":131072,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-18"},"id":"openrouter/google/gemini-3-pro-image","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.3675,"average_ttft":null,"average_latency":2.7372,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.3675,"average_ttft":null,"average_latency":2.7372,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3-pro-image-preview","base_model_name":"","max_context_window":65536,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-20"},"id":"openrouter/google/gemini-3-pro-image-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.0076,"average_ttft":null,"average_latency":2.6744,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.0076,"average_ttft":null,"average_latency":2.6744,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-image","base_model_name":"","max_context_window":131072,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-18"},"id":"openrouter/google/gemini-3.1-flash-image","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.7469,"average_ttft":null,"average_latency":0.8417,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.7469,"average_ttft":null,"average_latency":0.8417,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-image-preview","base_model_name":"","max_context_window":65536,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"openrouter/google/gemini-3.1-flash-image-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.7109,"average_ttft":null,"average_latency":0.6993,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7109,"average_ttft":null,"average_latency":0.6993,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-lite","base_model_name":"openrouter/google/gemini-3.1-flash-lite","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.024999999999999998,"cache_creation_input_cost":0.08333333333333334,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-05-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-3.1-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.8288,"average_ttft":null,"average_latency":0.6127,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.8288,"average_ttft":null,"average_latency":0.6127,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-lite-image","base_model_name":"","max_context_window":65536,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-30"},"id":"openrouter/google/gemini-3.1-flash-lite-image","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.9767,"average_ttft":null,"average_latency":1.2392,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.9767,"average_ttft":null,"average_latency":1.2392,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-lite-preview","base_model_name":"openrouter/google/gemini-3.1-flash-lite-preview","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.024999999999999998,"cache_creation_input_cost":0.08333333333333334,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-3.1-flash-lite-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.2901,"average_ttft":null,"average_latency":0.4137,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.2901,"average_ttft":null,"average_latency":0.4137,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-flash-lite:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.125,"output_cost":0.75,"cache_hit_input_cost":0.0125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-07"},"id":"openrouter/google/gemini-3.1-flash-lite:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-pro-preview","base_model_name":"openrouter/google/gemini-3.1-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.19999999999999998,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2026-02-19","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-3.1-pro-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":56.7316,"average_ttft":null,"average_latency":4.2242,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.7316,"average_ttft":null,"average_latency":4.2242,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-pro-preview-customtools","base_model_name":"openrouter/google/gemini-3.1-pro-preview-customtools","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.19999999999999998,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2026-02-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemini-3.1-pro-preview-customtools","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":29.2301,"average_ttft":null,"average_latency":2.0698,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":29.2301,"average_ttft":null,"average_latency":2.0698,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.1-pro-preview:batch","base_model_name":"","max_context_window":1048576,"input_cost":1,"output_cost":6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-19"},"id":"openrouter/google/gemini-3.1-pro-preview:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openrouter/google/gemini-3.5-flash","base_model_name":"google/gemini-3.5-flash","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0.0833333333333333,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"release_date":"2026-05-19"},"id":"openrouter/google/gemini-3.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":53.0741,"average_ttft":null,"average_latency":1.1871,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":53.0741,"average_ttft":null,"average_latency":1.1871,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.5-flash-lite","base_model_name":"openrouter/google/gemini-3.5-flash-lite","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0.0833333333333333,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-21"},"id":"openrouter/google/gemini-3.5-flash-lite","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.2349,"average_ttft":null,"average_latency":0.5717,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.2349,"average_ttft":null,"average_latency":0.5717,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.5-flash-lite:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":1.25,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-21"},"id":"openrouter/google/gemini-3.5-flash-lite:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.5-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-19"},"id":"openrouter/google/gemini-3.5-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.6-flash","base_model_name":"openrouter/google/gemini-3.6-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5038626982845081,"ci_lo":0.4297656202995626,"model":"gemini-3-6-flash","config":"mini_swe_agent_gemini_3_6_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.037048538992472776,"harness":"mini-swe-agent","version":"v1.1","n_passed":211,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":211,"pass_at_1":0.4668141592920354,"pass_at_4":0.7522123893805309,"pass_rate":0.4668141592920354,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.419013277333334,"n_tasks_in_set":113,"median_cost_usd":3.444695325000001,"mean_agent_steps":116.73333333333333,"reasoning_effort":"high","mean_cache_tokens":11254636.448888889,"mean_input_tokens":12595957.344444444,"n_tasks_attempted":113,"mean_output_tokens":95844.86222222222,"median_agent_steps":108,"n_tasks_passed_any":85,"median_input_tokens":8949018.5,"median_output_tokens":86727,"mean_duration_seconds":1477.8607510707964,"median_duration_seconds":1214.8670550000002,"median_peak_context_tokens":151398.5,"median_output_tokens_to_pass":83414}},"release_date":"2026-07-21"},"id":"openrouter/google/gemini-3.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":74.9392,"average_ttft":null,"average_latency":0.8153,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":74.9392,"average_ttft":null,"average_latency":0.8153,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.6-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.375,"output_cost":1.875,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-21"},"id":"openrouter/google/gemini-3.6-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.7-flash","base_model_name":"openrouter/google/gemini-3.7-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}},"release_date":"2026-08-13"},"id":"openrouter/google/gemini-3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":36.4806,"average_ttft":null,"average_latency":1.661,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.4806,"average_ttft":null,"average_latency":1.661,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.7-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.375,"output_cost":1.875,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-13"},"id":"openrouter/google/gemini-3.7-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.8-flash","base_model_name":"openrouter/google/gemini-3.8-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":0.7,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7524281656234058,"ci_lo":0.7240819014906883,"model":"gemini-3-8-flash","config":"mini_swe_agent_gemini_3_8_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.014173132066358783,"harness":"mini-swe-agent","version":"v1.1","n_passed":330,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":330,"pass_at_1":0.738255033557047,"pass_at_4":0.8584070796460177,"pass_rate":0.738255033557047,"n_attempted":447,"ci_attempted":447,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.362349413758389,"n_tasks_in_set":113,"median_cost_usd":2.1098912999999997,"mean_agent_steps":166.3131991051454,"reasoning_effort":"high","mean_cache_tokens":21456039.230425056,"mean_input_tokens":21734449.25279642,"n_tasks_attempted":113,"mean_output_tokens":143242.6644295302,"median_agent_steps":161,"n_tasks_passed_any":97,"median_input_tokens":18026661,"median_output_tokens":138377,"mean_duration_seconds":686.7691519843399,"median_duration_seconds":604.643838,"median_peak_context_tokens":215558,"median_output_tokens_to_pass":136617.5}},"release_date":"2026-09-02","is_available_on_credits":true},"id":"openrouter/google/gemini-3.8-flash","is_byok":false,"effective_discount_rate":0.7,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":104.2428,"average_ttft":3.6272,"average_latency":16.7093,"uptime_percent":99.0178,"cache_hit_percentage":34.272},"throughput":{"average_tps":104.2428,"average_ttft":3.6272,"average_latency":16.7093,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemini-3.8-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.375,"output_cost":1.875,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0.0416666666666667,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-02"},"id":"openrouter/google/gemini-3.8-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-2-27b-it","base_model_name":"openrouter/google/gemma-2-27b-it","max_context_window":8192,"input_cost":0.65,"output_cost":0.65,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/google/gemma-2-27b-it"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8192,"release_date":"2024-07-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemma-2-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.8744,"average_ttft":null,"average_latency":0.4877,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.8744,"average_ttft":null,"average_latency":0.4877,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-3-12b-it","base_model_name":"openrouter/google/gemma-3-12b-it","max_context_window":131072,"input_cost":0.049999999999999996,"output_cost":0.15,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-03-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemma-3-12b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.0228,"average_ttft":null,"average_latency":0.5359,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.0228,"average_ttft":null,"average_latency":0.5359,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-3-27b-it","base_model_name":"openrouter/google/gemma-3-27b-it","max_context_window":131072,"input_cost":0.08,"output_cost":0.44999999999999996,"cache_hit_input_cost":0.04,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-03-12","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.3915,"average_ttft":null,"average_latency":3.7741,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.3915,"average_ttft":null,"average_latency":3.7741,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-3-4b-it","base_model_name":"openrouter/google/gemma-3-4b-it","max_context_window":131072,"input_cost":0.049999999999999996,"output_cost":0.09999999999999999,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-03-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/google/gemma-3-4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.3572,"average_ttft":null,"average_latency":1.37,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3572,"average_ttft":null,"average_latency":1.37,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-4-26b-a4b-it","base_model_name":"openrouter/google/gemma-4-26b-a4b-it","max_context_window":262144,"input_cost":0.09,"output_cost":0.3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-03"},"id":"openrouter/google/gemma-4-26b-a4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":116.9926,"average_ttft":2.5909,"average_latency":3.7497,"uptime_percent":99.9522,"cache_hit_percentage":91.9414},"throughput":{"average_tps":116.9926,"average_ttft":2.5909,"average_latency":3.7497,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/google/gemma-4-31b-it","base_model_name":"openrouter/google/gemma-4-31b-it","max_context_window":262144,"input_cost":0.09,"output_cost":0.33999999999999997,"cache_hit_input_cost":0.05,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"openrouter/google/gemma-4-31b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.4625,"average_ttft":null,"average_latency":6.8992,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.4625,"average_ttft":null,"average_latency":6.8992,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/gryphe/mythomax-l2-13b","base_model_name":"","max_context_window":8192,"input_cost":0.08,"output_cost":0.11,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-07-02"},"id":"openrouter/gryphe/mythomax-l2-13b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":36.7155,"average_ttft":null,"average_latency":0.2724,"uptime_percent":100,"cache_hit_percentage":64.8649},"throughput":{"average_tps":36.7155,"average_ttft":null,"average_latency":0.2724,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/ibm-granite/granite-4.0-h-micro","base_model_name":"","max_context_window":131000,"input_cost":0.017,"output_cost":0.112,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-20"},"id":"openrouter/ibm-granite/granite-4.0-h-micro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.5144,"average_ttft":null,"average_latency":0.9098,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.5144,"average_ttft":null,"average_latency":0.9098,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/ibm-granite/granite-4.2-8b","base_model_name":"","max_context_window":131072,"input_cost":0.06,"output_cost":0.25,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-31"},"id":"openrouter/ibm-granite/granite-4.2-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":78.053,"average_ttft":null,"average_latency":0.82,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":78.053,"average_ttft":null,"average_latency":0.82,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inception/mercury-2","base_model_name":"","max_context_window":128000,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-04"},"id":"openrouter/inception/mercury-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":91.8862,"average_ttft":null,"average_latency":0.4221,"uptime_percent":100,"cache_hit_percentage":75},"throughput":{"average_tps":91.8862,"average_ttft":null,"average_latency":0.4221,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inception/mercury-2.5","base_model_name":"","max_context_window":260000,"input_cost":0.04,"output_cost":0.15,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-08"},"id":"openrouter/inception/mercury-2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":137.7631,"average_ttft":null,"average_latency":20.3114,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":137.7631,"average_ttft":null,"average_latency":20.3114,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inclusionai/ling-3.0-flash","base_model_name":"","max_context_window":262144,"input_cost":0.020999999999999998,"output_cost":0.063,"cache_hit_input_cost":0.0042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-23"},"id":"openrouter/inclusionai/ling-3.0-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":63.5744,"average_ttft":null,"average_latency":68.1399,"uptime_percent":100,"cache_hit_percentage":17.532},"throughput":{"average_tps":63.5744,"average_ttft":null,"average_latency":68.1399,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inclusionai/ling-3.0-flash-fin","base_model_name":"","max_context_window":262144,"input_cost":0.06,"output_cost":0.18,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27"},"id":"openrouter/inclusionai/ling-3.0-flash-fin","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":84.1702,"average_ttft":null,"average_latency":0.7483,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":84.1702,"average_ttft":null,"average_latency":0.7483,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inclusionai/ling-3.0-flash-vl","base_model_name":"","max_context_window":262144,"input_cost":0.021,"output_cost":0.0616,"cache_hit_input_cost":0.0042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"openrouter/inclusionai/ling-3.0-flash-vl","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":51.553,"average_ttft":null,"average_latency":1.0838,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":51.553,"average_ttft":null,"average_latency":1.0838,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inference-net/schematron-v2-small","base_model_name":"","max_context_window":128000,"input_cost":0.049999999999999996,"output_cost":0.22999999999999998,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-12"},"id":"openrouter/inference-net/schematron-v2-small","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":1.9271,"average_ttft":null,"average_latency":1.3044,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.9271,"average_ttft":null,"average_latency":1.3044,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/inference-net/schematron-v2-turbo","base_model_name":"","max_context_window":128000,"input_cost":0.03,"output_cost":0.15,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-12"},"id":"openrouter/inference-net/schematron-v2-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":48.1922,"average_ttft":null,"average_latency":1.5414,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.1922,"average_ttft":null,"average_latency":1.5414,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/kwaipilot/kat-coder-pro-v2.5","base_model_name":"","max_context_window":262144,"input_cost":0.74,"output_cost":2.96,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-10"},"id":"openrouter/kwaipilot/kat-coder-pro-v2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mancer/weaver","base_model_name":"","max_context_window":8000,"input_cost":0.39999999999999997,"output_cost":0.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-08-02"},"id":"openrouter/mancer/weaver","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":54.9286,"average_ttft":null,"average_latency":1.1714,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":54.9286,"average_ttft":null,"average_latency":1.1714,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meituan/longcat-2.0","base_model_name":"","max_context_window":1048756,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-20"},"id":"openrouter/meituan/longcat-2.0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.0186,"average_ttft":null,"average_latency":2.6688,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.0186,"average_ttft":null,"average_latency":2.6688,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-3.1-70b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.4,"output_cost":0.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/meta-llama/llama-3.1-70b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-07-23","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-3.1-70b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.2461,"average_ttft":null,"average_latency":35.1412,"uptime_percent":66.6667,"cache_hit_percentage":0},"throughput":{"average_tps":12.2461,"average_ttft":null,"average_latency":35.1412,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-3.1-8b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.049999999999999996,"output_cost":0.08,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/meta-llama/llama-3.1-8b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-07-23","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-3.1-8b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.1305,"average_ttft":null,"average_latency":0.5217,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.1305,"average_ttft":null,"average_latency":0.5217,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-3.2-1b-instruct","base_model_name":"","max_context_window":60000,"input_cost":0.027,"output_cost":0.201,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-09-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-3.2-1b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":47.8214,"average_ttft":null,"average_latency":0.3237,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":47.8214,"average_ttft":null,"average_latency":0.3237,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-3.2-3b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.049999999999999996,"output_cost":0.33,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/meta-llama/llama-3.2-3b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-09-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-3.2-3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.8264,"average_ttft":null,"average_latency":1.0434,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.8264,"average_ttft":null,"average_latency":1.0434,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-3.3-70b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.09999999999999999,"output_cost":0.32,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-12-06","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-3.3-70b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.5127,"average_ttft":null,"average_latency":0.5327,"uptime_percent":100,"cache_hit_percentage":32.3232},"throughput":{"average_tps":10.5127,"average_ttft":null,"average_latency":0.5327,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-4-maverick","base_model_name":"","max_context_window":1048576,"input_cost":0.1875,"output_cost":0.6525,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-04-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-4-maverick","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":48.211,"average_ttft":null,"average_latency":3.8349,"uptime_percent":100,"cache_hit_percentage":1.1962},"throughput":{"average_tps":48.211,"average_ttft":null,"average_latency":3.8349,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-4-scout","base_model_name":"","max_context_window":1310720,"input_cost":0.09999999999999999,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":10000000,"release_date":"2025-04-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/meta-llama/llama-4-scout","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.9492,"average_ttft":null,"average_latency":0.7035,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.9492,"average_ttft":null,"average_latency":0.7035,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta-llama/llama-guard-4-12b","base_model_name":"","max_context_window":163840,"input_cost":0.18,"output_cost":0.18,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-30"},"id":"openrouter/meta-llama/llama-guard-4-12b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.3774,"average_ttft":null,"average_latency":0.3415,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.3774,"average_ttft":null,"average_latency":0.3415,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-glimmer-30b","base_model_name":"","max_context_window":131072,"input_cost":0.35,"output_cost":1.5,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-09"},"id":"openrouter/meta/muse-glimmer-30b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":66.9663,"average_ttft":null,"average_latency":0.6856,"uptime_percent":100,"cache_hit_percentage":88.6957},"throughput":{"average_tps":66.9663,"average_ttft":null,"average_latency":0.6856,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-spark-1.1","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5635392652473017,"ci_lo":0.5028324161686275,"model":"muse-spark-1-1","config":"mini_swe_agent_muse_spark_1_1_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.030353424539337114,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.7964601769911505,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.361142644469026,"n_tasks_in_set":113,"median_cost_usd":1.7171158,"mean_agent_steps":95.82522123893806,"reasoning_effort":"xhigh","mean_cache_tokens":11781947.471238937,"mean_input_tokens":12005399.261061948,"n_tasks_attempted":113,"mean_output_tokens":74008.4203539823,"median_agent_steps":86,"n_tasks_passed_any":90,"median_input_tokens":8037064.5,"median_output_tokens":66088,"mean_duration_seconds":897.5133296747788,"median_duration_seconds":688.5861825,"median_peak_context_tokens":154817.5,"median_output_tokens_to_pass":61398}},"release_date":"2026-07-16"},"id":"openrouter/meta/muse-spark-1.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":86.6882,"average_ttft":null,"average_latency":0.7385,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":86.6882,"average_ttft":null,"average_latency":0.7385,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-spark-1.2","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5699155383909527,"ci_lo":0.5274295943524101,"model":"muse-spark-1-2","config":"mini_swe_agent_muse_spark_1_2_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02124297201927127,"harness":"mini-swe-agent","version":"v1.1","n_passed":248,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":248,"pass_at_1":0.5486725663716814,"pass_at_4":0.8141592920353983,"pass_rate":0.5486725663716814,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.6955048180309733,"n_tasks_in_set":113,"median_cost_usd":2.6840506,"mean_agent_steps":100.75884955752213,"reasoning_effort":"xhigh","mean_cache_tokens":12584988.949115044,"mean_input_tokens":13693824.435840707,"n_tasks_attempted":113,"mean_output_tokens":99226.38053097345,"median_agent_steps":94,"n_tasks_passed_any":92,"median_input_tokens":10339991,"median_output_tokens":81250,"mean_duration_seconds":927.8692516349557,"median_duration_seconds":784.787489,"median_peak_context_tokens":189481,"median_output_tokens_to_pass":77863}},"release_date":"2026-08-05"},"id":"openrouter/meta/muse-spark-1.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":64.7478,"average_ttft":null,"average_latency":1.067,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":64.7478,"average_ttft":null,"average_latency":1.067,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-spark-1.2-contributor","base_model_name":"","max_context_window":1048576,"input_cost":0.09999999999999999,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.002,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-21"},"id":"openrouter/meta/muse-spark-1.2-contributor","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-spark-1.3","base_model_name":"","max_context_window":1048576,"input_cost":1.25,"output_cost":4.25,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-02"},"id":"openrouter/meta/muse-spark-1.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":26.8891,"average_ttft":null,"average_latency":1.8581,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.8891,"average_ttft":null,"average_latency":1.8581,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/meta/muse-spark-1.3-contributor","base_model_name":"","max_context_window":1048576,"input_cost":0.09999999999999999,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.002,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-02"},"id":"openrouter/meta/muse-spark-1.3-contributor","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/microsoft/phi-4","base_model_name":"","max_context_window":16384,"input_cost":0.07,"output_cost":0.14,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16384,"release_date":"2025-01-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/microsoft/phi-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":63.8464,"average_ttft":null,"average_latency":1.0043,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":63.8464,"average_ttft":null,"average_latency":1.0043,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/microsoft/wizardlm-2-8x22b","base_model_name":"","max_context_window":65535,"input_cost":0.62,"output_cost":0.62,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/microsoft/wizardlm-2-8x22b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":65536,"release_date":"2024-04-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/microsoft/wizardlm-2-8x22b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.0074,"average_ttft":null,"average_latency":1.944,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.0074,"average_ttft":null,"average_latency":1.944,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-01","base_model_name":"","max_context_window":1000192,"input_cost":0.19999999999999998,"output_cost":1.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-15"},"id":"openrouter/minimax/minimax-01","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.8125,"average_ttft":null,"average_latency":1.1189,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.8125,"average_ttft":null,"average_latency":1.1189,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m1","base_model_name":"","max_context_window":1000000,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-17"},"id":"openrouter/minimax/minimax-m1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.1807,"average_ttft":null,"average_latency":3.4077,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.1807,"average_ttft":null,"average_latency":3.4077,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m2","base_model_name":"","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-23"},"id":"openrouter/minimax/minimax-m2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":29.4434,"average_ttft":null,"average_latency":1.4204,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":29.4434,"average_ttft":null,"average_latency":1.4204,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m2-her","base_model_name":"","max_context_window":65536,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-23"},"id":"openrouter/minimax/minimax-m2-her","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.3523,"average_ttft":null,"average_latency":0.7218,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3523,"average_ttft":null,"average_latency":0.7218,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m2.1","base_model_name":"","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-23","expiration_date":"2026-10-08"},"id":"openrouter/minimax/minimax-m2.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":39.39,"average_ttft":null,"average_latency":1.4504,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":39.39,"average_ttft":null,"average_latency":1.4504,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m2.5","base_model_name":"","max_context_window":204800,"input_cost":0.27,"output_cost":1.08,"cache_hit_input_cost":0.027,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-12"},"id":"openrouter/minimax/minimax-m2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":21.531,"average_ttft":null,"average_latency":2.9723,"uptime_percent":100,"cache_hit_percentage":60.0939},"throughput":{"average_tps":21.531,"average_ttft":null,"average_latency":2.9723,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m2.7","base_model_name":"","max_context_window":204800,"input_cost":0.21,"output_cost":0.84,"cache_hit_input_cost":0.042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-18"},"id":"openrouter/minimax/minimax-m2.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":101.5817,"average_ttft":null,"average_latency":5.3713,"uptime_percent":95.3116,"cache_hit_percentage":0},"throughput":{"average_tps":101.5817,"average_ttft":null,"average_latency":5.3713,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/minimax/minimax-m3","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-31"},"id":"openrouter/minimax/minimax-m3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.8639,"average_ttft":null,"average_latency":1.7947,"uptime_percent":100,"cache_hit_percentage":81.457},"throughput":{"average_tps":30.8639,"average_ttft":null,"average_latency":1.7947,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/codestral-2508","base_model_name":"openrouter/mistralai/codestral-2508","max_context_window":256000,"input_cost":0.3,"output_cost":0.8999999999999999,"cache_hit_input_cost":0.03,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":256000,"release_date":"2025-08-01","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/codestral-2508","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.8788,"average_ttft":null,"average_latency":0.402,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.8788,"average_ttft":null,"average_latency":0.402,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/codestral-2508:batch","base_model_name":"","max_context_window":256000,"input_cost":0.15,"output_cost":0.44999999999999996,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-01"},"id":"openrouter/mistralai/codestral-2508:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/devstral-2512","base_model_name":"openrouter/mistralai/devstral-2512","max_context_window":262144,"input_cost":0.39999999999999997,"output_cost":2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-09"},"id":"openrouter/mistralai/devstral-2512","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.4396,"average_ttft":null,"average_latency":0.5896,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.4396,"average_ttft":null,"average_latency":0.5896,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/ministral-14b-2512","base_model_name":"openrouter/mistralai/ministral-14b-2512","max_context_window":262144,"input_cost":0.19999999999999998,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.02,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"openrouter/mistralai/ministral-14b-2512","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":31.3336,"average_ttft":null,"average_latency":1.6889,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.3336,"average_ttft":null,"average_latency":1.6889,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/ministral-3b-2512","base_model_name":"openrouter/mistralai/ministral-3b-2512","max_context_window":131072,"input_cost":0.09999999999999999,"output_cost":0.09999999999999999,"cache_hit_input_cost":0.01,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"openrouter/mistralai/ministral-3b-2512","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":67.4013,"average_ttft":null,"average_latency":0.6136,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":67.4013,"average_ttft":null,"average_latency":0.6136,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/ministral-8b-2512","base_model_name":"openrouter/mistralai/ministral-8b-2512","max_context_window":262144,"input_cost":0.15,"output_cost":0.15,"cache_hit_input_cost":0.015,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"openrouter/mistralai/ministral-8b-2512","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":53.3796,"average_ttft":null,"average_latency":1.0427,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":53.3796,"average_ttft":null,"average_latency":1.0427,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/ministral-8b-2512:batch","base_model_name":"","max_context_window":262144,"input_cost":0.075,"output_cost":0.075,"cache_hit_input_cost":0.0075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02"},"id":"openrouter/mistralai/ministral-8b-2512:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-large","base_model_name":"openrouter/mistralai/mistral-large","max_context_window":128000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/mistralai/mistral-large"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-02-26","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/mistral-large","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.8433,"average_ttft":null,"average_latency":2.2723,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.8433,"average_ttft":null,"average_latency":2.2723,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-large-2407","base_model_name":"openrouter/mistralai/mistral-large-2407","max_context_window":131072,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/mistralai/mistral-large-2407"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-11-19","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/mistral-large-2407","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.6953,"average_ttft":null,"average_latency":0.5899,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.6953,"average_ttft":null,"average_latency":0.5899,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-large-2512","base_model_name":"openrouter/mistralai/mistral-large-2512","max_context_window":262144,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0.049999999999999996,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2024-07-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/mistral-large-2512","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.5895,"average_ttft":null,"average_latency":0.6314,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.5895,"average_ttft":null,"average_latency":0.6314,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-large-2512:batch","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-01"},"id":"openrouter/mistralai/mistral-large-2512:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-medium-3","base_model_name":"openrouter/mistralai/mistral-medium-3","max_context_window":131072,"input_cost":0.39999999999999997,"output_cost":2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-05-07"},"id":"openrouter/mistralai/mistral-medium-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.9145,"average_ttft":null,"average_latency":1.0086,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.9145,"average_ttft":null,"average_latency":1.0086,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-medium-3-5","base_model_name":"openrouter/mistralai/mistral-medium-3-5","max_context_window":262144,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-30"},"id":"openrouter/mistralai/mistral-medium-3-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":124.9578,"average_ttft":null,"average_latency":5.064,"uptime_percent":100,"cache_hit_percentage":88.5129},"throughput":{"average_tps":124.9578,"average_ttft":null,"average_latency":5.064,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-medium-3-5:batch","base_model_name":"","max_context_window":262144,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-30"},"id":"openrouter/mistralai/mistral-medium-3-5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-medium-3.1","base_model_name":"openrouter/mistralai/mistral-medium-3.1","max_context_window":131072,"input_cost":0.39999999999999997,"output_cost":2,"cache_hit_input_cost":0.04,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13"},"id":"openrouter/mistralai/mistral-medium-3.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.6162,"average_ttft":null,"average_latency":0.4422,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.6162,"average_ttft":null,"average_latency":0.4422,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-medium-3.1:batch","base_model_name":"","max_context_window":131072,"input_cost":0.19999999999999998,"output_cost":1,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13"},"id":"openrouter/mistralai/mistral-medium-3.1:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-nemo","base_model_name":"openrouter/mistralai/mistral-nemo","max_context_window":131072,"input_cost":0.019000000000000003,"output_cost":0.03,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/mistralai/mistral-nemo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-19","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/mistral-nemo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":34.8605,"average_ttft":null,"average_latency":0.8734,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.8605,"average_ttft":null,"average_latency":0.8734,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-saba","base_model_name":"openrouter/mistralai/mistral-saba","max_context_window":32768,"input_cost":0.19999999999999998,"output_cost":0.6,"cache_hit_input_cost":0.02,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-02-17"},"id":"openrouter/mistralai/mistral-saba","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":33.2015,"average_ttft":null,"average_latency":0.3915,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":33.2015,"average_ttft":null,"average_latency":0.3915,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-small-24b-instruct-2501","base_model_name":"openrouter/mistralai/mistral-small-24b-instruct-2501","max_context_window":32768,"input_cost":0.049999999999999996,"output_cost":0.08,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-30"},"id":"openrouter/mistralai/mistral-small-24b-instruct-2501","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.0235,"average_ttft":null,"average_latency":0.83,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.0235,"average_ttft":null,"average_latency":0.83,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-small-2603","base_model_name":"openrouter/mistralai/mistral-small-2603","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-16"},"id":"openrouter/mistralai/mistral-small-2603","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":27.7863,"average_ttft":null,"average_latency":0.4679,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":27.7863,"average_ttft":null,"average_latency":0.4679,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-small-2603:batch","base_model_name":"","max_context_window":262144,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0.0075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-16"},"id":"openrouter/mistralai/mistral-small-2603:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-small-3.1-24b-instruct","base_model_name":"openrouter/mistralai/mistral-small-3.1-24b-instruct","max_context_window":128000,"input_cost":0.351,"output_cost":0.5549999999999999,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-17"},"id":"openrouter/mistralai/mistral-small-3.1-24b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.9495,"average_ttft":null,"average_latency":0.6913,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.9495,"average_ttft":null,"average_latency":0.6913,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mistral-small-3.2-24b-instruct","base_model_name":"openrouter/mistralai/mistral-small-3.2-24b-instruct","max_context_window":256000,"input_cost":0.09375,"output_cost":0.25,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-06-20"},"id":"openrouter/mistralai/mistral-small-3.2-24b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.6498,"average_ttft":null,"average_latency":1.3439,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.6498,"average_ttft":null,"average_latency":1.3439,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/mistralai/mixtral-8x22b-instruct","base_model_name":"openrouter/mistralai/mixtral-8x22b-instruct","max_context_window":65536,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/mistralai/mixtral-8x22b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":65536,"release_date":"2024-04-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/mistralai/mixtral-8x22b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.5652,"average_ttft":null,"average_latency":0.3992,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.5652,"average_ttft":null,"average_latency":0.3992,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openrouter/mistralai/voxtral-small-24b-2507","base_model_name":"mistralai/voxtral-small-24b-2507","max_context_window":32768,"input_cost":0.09999999999999999,"output_cost":0.3,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-30"},"id":"openrouter/mistralai/voxtral-small-24b-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":95.7673,"average_ttft":null,"average_latency":0.6683,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":95.7673,"average_ttft":null,"average_latency":0.6683,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2","base_model_name":"","max_context_window":131072,"input_cost":0.5700000000000001,"output_cost":2.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"context_size":131072,"release_date":"2025-07-11","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/moonshotai/kimi-k2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.4937,"average_ttft":null,"average_latency":0.9534,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.4937,"average_ttft":null,"average_latency":0.9534,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2-0905","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-09-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/moonshotai/kimi-k2-0905","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.534,"average_ttft":null,"average_latency":2.1975,"uptime_percent":100,"cache_hit_percentage":44.4444},"throughput":{"average_tps":16.534,"average_ttft":null,"average_latency":2.1975,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-11-06","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/moonshotai/kimi-k2-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":86.4549,"average_ttft":null,"average_latency":0.8132,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":86.4549,"average_ttft":null,"average_latency":0.8132,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2.5","base_model_name":"","max_context_window":262144,"input_cost":0.44999999999999996,"output_cost":2.25,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-27"},"id":"openrouter/moonshotai/kimi-k2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.1722,"average_ttft":null,"average_latency":3.0397,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.1722,"average_ttft":null,"average_latency":3.0397,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2.6","base_model_name":"","max_context_window":262144,"input_cost":0.43415,"output_cost":1.828,"cache_hit_input_cost":0.07312,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-20"},"id":"openrouter/moonshotai/kimi-k2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":48.215,"average_ttft":null,"average_latency":46.063,"uptime_percent":100,"cache_hit_percentage":66.1186},"throughput":{"average_tps":48.215,"average_ttft":null,"average_latency":46.063,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k2.7-code","base_model_name":"","max_context_window":262144,"input_cost":0.6712,"output_cost":3.35,"cache_hit_input_cost":0.18,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"release_date":"2026-06-12"},"id":"openrouter/moonshotai/kimi-k2.7-code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":104.2255,"average_ttft":1.9739,"average_latency":6.9984,"uptime_percent":100,"cache_hit_percentage":81.3492},"throughput":{"average_tps":104.2255,"average_ttft":1.9739,"average_latency":6.9984,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k3","base_model_name":"","max_context_window":1048576,"input_cost":0.7264,"output_cost":10,"cache_hit_input_cost":0.7264,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16"},"id":"openrouter/moonshotai/kimi-k3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.4679,"average_ttft":null,"average_latency":3.6842,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.4679,"average_ttft":null,"average_latency":3.6842,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/moonshotai/kimi-k3:batch","base_model_name":"","max_context_window":1048576,"input_cost":2.28,"output_cost":11.4,"cache_hit_input_cost":0.228,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-16"},"id":"openrouter/moonshotai/kimi-k3:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/morph/morph-v3-fast","base_model_name":"","max_context_window":81920,"input_cost":0.7999999999999999,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-07"},"id":"openrouter/morph/morph-v3-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4058.5636,"average_ttft":null,"average_latency":4.0533,"uptime_percent":100,"cache_hit_percentage":89.8876},"throughput":{"average_tps":4058.5636,"average_ttft":null,"average_latency":4.0533,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/morph/morph-v3-large","base_model_name":"","max_context_window":262144,"input_cost":0.8999999999999999,"output_cost":1.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-07"},"id":"openrouter/morph/morph-v3-large","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.6507,"average_ttft":null,"average_latency":7.5574,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.6507,"average_ttft":null,"average_latency":7.5574,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nex-agi/nex-n2.5-mini","base_model_name":"","max_context_window":262144,"input_cost":0.025,"output_cost":0.1,"cache_hit_input_cost":0.0025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-08","is_available_on_credits":true},"id":"openrouter/nex-agi/nex-n2.5-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nex-agi/nex-n2.5-pro","base_model_name":"","max_context_window":262144,"input_cost":0.075,"output_cost":0.25,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-08","is_available_on_credits":true},"id":"openrouter/nex-agi/nex-n2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nousresearch/hermes-3-llama-3.1-405b","base_model_name":"","max_context_window":131072,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/nousresearch/hermes-3-llama-3.1-405b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-08-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/nousresearch/hermes-3-llama-3.1-405b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.8513,"average_ttft":null,"average_latency":1.6499,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.8513,"average_ttft":null,"average_latency":1.6499,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nousresearch/hermes-3-llama-3.1-70b","base_model_name":"","max_context_window":131072,"input_cost":0.7,"output_cost":0.7,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-08-18","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/nousresearch/hermes-3-llama-3.1-70b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.0732,"average_ttft":null,"average_latency":1.9984,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.0732,"average_ttft":null,"average_latency":1.9984,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nousresearch/hermes-4-405b","base_model_name":"","max_context_window":131072,"input_cost":1,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-26"},"id":"openrouter/nousresearch/hermes-4-405b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.1895,"average_ttft":null,"average_latency":0.5509,"uptime_percent":100,"cache_hit_percentage":64},"throughput":{"average_tps":24.1895,"average_ttft":null,"average_latency":0.5509,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nvidia/nemotron-3-nano-30b-a3b","base_model_name":"","max_context_window":262144,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-14"},"id":"openrouter/nvidia/nemotron-3-nano-30b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":108.4273,"average_ttft":null,"average_latency":0.3169,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":108.4273,"average_ttft":null,"average_latency":0.3169,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nvidia/nemotron-3-super-120b-a12b","base_model_name":"","max_context_window":262144,"input_cost":0.08,"output_cost":0.44999999999999996,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-11"},"id":"openrouter/nvidia/nemotron-3-super-120b-a12b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.5014,"average_ttft":null,"average_latency":7.337,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.5014,"average_ttft":null,"average_latency":7.337,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nvidia/nemotron-3-ultra-550b-a55b","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0.12,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-04"},"id":"openrouter/nvidia/nemotron-3-ultra-550b-a55b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":60.812,"average_ttft":null,"average_latency":0.7374,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":60.812,"average_ttft":null,"average_latency":0.7374,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nvidia/nemotron-3.5-content-safety","base_model_name":"","max_context_window":131072,"input_cost":0.19999999999999998,"output_cost":0.19999999999999998,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-04"},"id":"openrouter/nvidia/nemotron-3.5-content-safety","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":137.0931,"average_ttft":null,"average_latency":0.5142,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":137.0931,"average_ttft":null,"average_latency":0.5142,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/nvidia/nemotron-3.5-lightning","base_model_name":"","max_context_window":262144,"input_cost":0.0595,"output_cost":0.17,"cache_hit_input_cost":0.02975,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-11"},"id":"openrouter/nvidia/nemotron-3.5-lightning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":144.4407,"average_ttft":null,"average_latency":0.4947,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":144.4407,"average_ttft":null,"average_latency":0.4947,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-3.5-turbo","base_model_name":"openrouter/openai/gpt-3.5-turbo","max_context_window":16385,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16385,"release_date":"2023-05-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-3.5-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":20.3624,"average_ttft":null,"average_latency":0.4492,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.3624,"average_ttft":null,"average_latency":0.4492,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-3.5-turbo-0613","base_model_name":"openrouter/openai/gpt-3.5-turbo-0613","max_context_window":4095,"input_cost":1,"output_cost":2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4095,"release_date":"2024-01-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-3.5-turbo-0613","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.0632,"average_ttft":null,"average_latency":0.409,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.0632,"average_ttft":null,"average_latency":0.409,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-3.5-turbo-16k","base_model_name":"openrouter/openai/gpt-3.5-turbo-16k","max_context_window":16385,"input_cost":3,"output_cost":4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":16385,"release_date":"2023-08-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-3.5-turbo-16k","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.3678,"average_ttft":null,"average_latency":0.4908,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.3678,"average_ttft":null,"average_latency":0.4908,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-3.5-turbo-instruct","base_model_name":"openrouter/openai/gpt-3.5-turbo-instruct","max_context_window":4095,"input_cost":1.5,"output_cost":2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-3.5-turbo-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":4095,"release_date":"2023-09-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-3.5-turbo-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.2598,"average_ttft":null,"average_latency":1.88,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.2598,"average_ttft":null,"average_latency":1.88,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-3.5-turbo:batch","base_model_name":"","max_context_window":16385,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-05-28"},"id":"openrouter/openai/gpt-3.5-turbo:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4","base_model_name":"openrouter/openai/gpt-4","max_context_window":8191,"input_cost":30,"output_cost":60,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8191,"release_date":"2023-05-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.4206,"average_ttft":null,"average_latency":0.88,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.4206,"average_ttft":null,"average_latency":0.88,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4-turbo","base_model_name":"openrouter/openai/gpt-4-turbo","max_context_window":128000,"input_cost":10,"output_cost":30,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4-turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-04-09","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.3546,"average_ttft":null,"average_latency":1.4163,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.3546,"average_ttft":null,"average_latency":1.4163,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4-turbo:batch","base_model_name":"","max_context_window":128000,"input_cost":5,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-09"},"id":"openrouter/openai/gpt-4-turbo:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1","base_model_name":"openrouter/openai/gpt-4.1","max_context_window":1047576,"input_cost":2,"output_cost":8,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1047576,"release_date":"2025-04-14","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.2978,"average_ttft":null,"average_latency":0.9016,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.2978,"average_ttft":null,"average_latency":0.9016,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1-mini","base_model_name":"openrouter/openai/gpt-4.1-mini","max_context_window":1047576,"input_cost":0.39999999999999997,"output_cost":1.5999999999999999,"cache_hit_input_cost":0.09999999999999999,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1047576,"release_date":"2025-04-14","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4.1-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.4992,"average_ttft":null,"average_latency":0.876,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.4992,"average_ttft":null,"average_latency":0.876,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1-mini:batch","base_model_name":"","max_context_window":1047576,"input_cost":0.19999999999999998,"output_cost":0.7999999999999999,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-14"},"id":"openrouter/openai/gpt-4.1-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1-nano","base_model_name":"openrouter/openai/gpt-4.1-nano","max_context_window":1047576,"input_cost":0.09999999999999999,"output_cost":0.39999999999999997,"cache_hit_input_cost":0.024999999999999998,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1047576,"release_date":"2025-04-14","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4.1-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":24.9374,"average_ttft":null,"average_latency":0.7916,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.9374,"average_ttft":null,"average_latency":0.7916,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1-nano:batch","base_model_name":"","max_context_window":1047576,"input_cost":0.049999999999999996,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.0125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-14"},"id":"openrouter/openai/gpt-4.1-nano:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4.1:batch","base_model_name":"","max_context_window":1047576,"input_cost":1,"output_cost":4,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-14"},"id":"openrouter/openai/gpt-4.1:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o","base_model_name":"openrouter/openai/gpt-4o","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-05-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.3135,"average_ttft":null,"average_latency":0.5884,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.3135,"average_ttft":null,"average_latency":0.5884,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-2024-05-13","base_model_name":"openrouter/openai/gpt-4o-2024-05-13","max_context_window":128000,"input_cost":5,"output_cost":15,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o-2024-05-13"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-05-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o-2024-05-13","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.1634,"average_ttft":null,"average_latency":1.116,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.1634,"average_ttft":null,"average_latency":1.116,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-2024-08-06","base_model_name":"openrouter/openai/gpt-4o-2024-08-06","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o-2024-08-06"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-08-06","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o-2024-08-06","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.7345,"average_ttft":null,"average_latency":0.6622,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.7345,"average_ttft":null,"average_latency":0.6622,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-2024-11-20","base_model_name":"openrouter/openai/gpt-4o-2024-11-20","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o-2024-11-20"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-11-20","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o-2024-11-20","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.5032,"average_ttft":null,"average_latency":0.6021,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.5032,"average_ttft":null,"average_latency":0.6021,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-mini","base_model_name":"openrouter/openai/gpt-4o-mini","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-18","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.6434,"average_ttft":0.5114,"average_latency":0.8199,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.6434,"average_ttft":0.5114,"average_latency":0.8199,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-mini-2024-07-18","base_model_name":"openrouter/openai/gpt-4o-mini-2024-07-18","max_context_window":128000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-4o-mini-2024-07-18"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-07-18","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-4o-mini-2024-07-18","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.0914,"average_ttft":null,"average_latency":0.4593,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.0914,"average_ttft":null,"average_latency":0.4593,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o-mini:batch","base_model_name":"","max_context_window":128000,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-18"},"id":"openrouter/openai/gpt-4o-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-4o:batch","base_model_name":"","max_context_window":128000,"input_cost":1.25,"output_cost":5,"cache_hit_input_cost":0.625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-05-13"},"id":"openrouter/openai/gpt-4o:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5","base_model_name":"openrouter/openai/gpt-5","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-5"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":400000,"release_date":"2025-08-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":18.8735,"average_ttft":null,"average_latency":1.8882,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.8735,"average_ttft":null,"average_latency":1.8882,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-image","base_model_name":"","max_context_window":400000,"input_cost":10,"output_cost":10,"cache_hit_input_cost":1.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-14"},"id":"openrouter/openai/gpt-5-image","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.7154,"average_ttft":null,"average_latency":2.9477,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7154,"average_ttft":null,"average_latency":2.9477,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-image-mini","base_model_name":"","max_context_window":400000,"input_cost":2.5,"output_cost":2,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-16"},"id":"openrouter/openai/gpt-5-image-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.1679,"average_ttft":null,"average_latency":2.0033,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":14.1679,"average_ttft":null,"average_latency":2.0033,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-mini","base_model_name":"openrouter/openai/gpt-5-mini","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-5-mini"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":28.1068,"average_ttft":null,"average_latency":2.4095,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.1068,"average_ttft":null,"average_latency":2.4095,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-mini:batch","base_model_name":"","max_context_window":400000,"input_cost":0.125,"output_cost":1,"cache_hit_input_cost":0.0125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-07"},"id":"openrouter/openai/gpt-5-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-nano","base_model_name":"openrouter/openai/gpt-5-nano","max_context_window":400000,"input_cost":0.049999999999999996,"output_cost":0.39999999999999997,"cache_hit_input_cost":0.005,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/gpt-5-nano"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-08-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":80.9274,"average_ttft":null,"average_latency":4.4832,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":80.9274,"average_ttft":null,"average_latency":4.4832,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-nano:batch","base_model_name":"","max_context_window":400000,"input_cost":0.024999999999999998,"output_cost":0.19999999999999998,"cache_hit_input_cost":0.0025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-07"},"id":"openrouter/openai/gpt-5-nano:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-pro","base_model_name":"openrouter/openai/gpt-5-pro","max_context_window":400000,"input_cost":15,"output_cost":120,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":400000,"release_date":"2025-10-06","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.5603,"average_ttft":null,"average_latency":15.3827,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.5603,"average_ttft":null,"average_latency":15.3827,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5-pro:batch","base_model_name":"","max_context_window":400000,"input_cost":7.5,"output_cost":60,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-06"},"id":"openrouter/openai/gpt-5-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5:batch","base_model_name":"","max_context_window":400000,"input_cost":0.625,"output_cost":5,"cache_hit_input_cost":0.0625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-07"},"id":"openrouter/openai/gpt-5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.1","base_model_name":"openrouter/openai/gpt-5.1","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.9776,"average_ttft":null,"average_latency":1.238,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.9776,"average_ttft":null,"average_latency":1.238,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.1-codex","base_model_name":"openrouter/openai/gpt-5.1-codex","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.13,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.1-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.0086,"average_ttft":null,"average_latency":1.4892,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.0086,"average_ttft":null,"average_latency":1.4892,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.1-codex-max","base_model_name":"openrouter/openai/gpt-5.1-codex-max","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-12-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.1-codex-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.0152,"average_ttft":null,"average_latency":3.9368,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.0152,"average_ttft":null,"average_latency":3.9368,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.1-codex-mini","base_model_name":"openrouter/openai/gpt-5.1-codex-mini","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2025-11-13","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.1-codex-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.4956,"average_ttft":null,"average_latency":20.8544,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.4956,"average_ttft":null,"average_latency":20.8544,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.1:batch","base_model_name":"","max_context_window":400000,"input_cost":0.625,"output_cost":5,"cache_hit_input_cost":0.0625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-13"},"id":"openrouter/openai/gpt-5.1:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2","base_model_name":"openrouter/openai/gpt-5.2","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.5505,"average_ttft":null,"average_latency":2.3821,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.5505,"average_ttft":null,"average_latency":2.3821,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2-chat","base_model_name":"openrouter/openai/gpt-5.2-chat","max_context_window":128000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-12-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.2-chat","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2-codex","base_model_name":"openrouter/openai/gpt-5.2-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-01-14","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.2-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":7.5572,"average_ttft":null,"average_latency":4.2118,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.5572,"average_ttft":null,"average_latency":4.2118,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2-pro","base_model_name":"openrouter/openai/gpt-5.2-pro","max_context_window":400000,"input_cost":21,"output_cost":168,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":400000,"release_date":"2025-12-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.2-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":2.4922,"average_ttft":null,"average_latency":5.7245,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.4922,"average_ttft":null,"average_latency":5.7245,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2-pro:batch","base_model_name":"","max_context_window":400000,"input_cost":10.5,"output_cost":84,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-10"},"id":"openrouter/openai/gpt-5.2-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.2:batch","base_model_name":"","max_context_window":400000,"input_cost":0.875,"output_cost":7,"cache_hit_input_cost":0.0875,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-10"},"id":"openrouter/openai/gpt-5.2:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.3-codex","base_model_name":"openrouter/openai/gpt-5.3-codex","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"release_date":"2026-02-24"},"id":"openrouter/openai/gpt-5.3-codex","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.0388,"average_ttft":null,"average_latency":0.8221,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.0388,"average_ttft":null,"average_latency":0.8221,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4","base_model_name":"openrouter/openai/gpt-5.4","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.0087,"average_ttft":null,"average_latency":0.847,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.0087,"average_ttft":null,"average_latency":0.847,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-image-2","base_model_name":"","max_context_window":272000,"input_cost":8,"output_cost":15,"cache_hit_input_cost":2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-21"},"id":"openrouter/openai/gpt-5.4-image-2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.8027,"average_ttft":null,"average_latency":0.9376,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.8027,"average_ttft":null,"average_latency":0.9376,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-mini","base_model_name":"openrouter/openai/gpt-5.4-mini","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.4-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":57.853,"average_ttft":null,"average_latency":2.3837,"uptime_percent":100,"cache_hit_percentage":89.5169},"throughput":{"average_tps":57.853,"average_ttft":null,"average_latency":2.3837,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-mini:batch","base_model_name":"","max_context_window":400000,"input_cost":0.375,"output_cost":2.25,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-17"},"id":"openrouter/openai/gpt-5.4-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-nano","base_model_name":"openrouter/openai/gpt-5.4-nano","max_context_window":400000,"input_cost":0.19999999999999998,"output_cost":1.25,"cache_hit_input_cost":0.02,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":400000,"release_date":"2026-03-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.4-nano","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.6553,"average_ttft":null,"average_latency":0.6891,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.6553,"average_ttft":null,"average_latency":0.6891,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-nano:batch","base_model_name":"","max_context_window":400000,"input_cost":0.09999999999999999,"output_cost":0.625,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-17"},"id":"openrouter/openai/gpt-5.4-nano:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-pro","base_model_name":"openrouter/openai/gpt-5.4-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}},"context_size":1050000,"release_date":"2026-03-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":2.157,"average_ttft":null,"average_latency":5.1214,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":2.157,"average_ttft":null,"average_latency":5.1214,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":15,"output_cost":90,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-05"},"id":"openrouter/openai/gpt-5.4-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.4:batch","base_model_name":"","max_context_window":1050000,"input_cost":1.25,"output_cost":7.5,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-05"},"id":"openrouter/openai/gpt-5.4:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.5","base_model_name":"openrouter/openai/gpt-5.5","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":1050000,"release_date":"2026-04-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":10.9331,"average_ttft":null,"average_latency":1.8179,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.9331,"average_ttft":null,"average_latency":1.8179,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.5-pro","base_model_name":"openrouter/openai/gpt-5.5-pro","max_context_window":1050000,"input_cost":30,"output_cost":180,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"context_size":1050000,"release_date":"2026-04-24","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":4.8739,"average_ttft":null,"average_latency":6.8133,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.8739,"average_ttft":null,"average_latency":6.8133,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.5-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":15,"output_cost":90,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-24"},"id":"openrouter/openai/gpt-5.5-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.5:batch","base_model_name":"","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-24"},"id":"openrouter/openai/gpt-5.5:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-luna","base_model_name":"openrouter/openai/gpt-5.6-luna","max_context_window":1050000,"input_cost":0.19999999999999998,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}},"context_size":1050000,"release_date":"2026-07-09","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-5.6-luna","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":83.958,"average_ttft":null,"average_latency":49.2157,"uptime_percent":100,"cache_hit_percentage":97.6354},"throughput":{"average_tps":83.958,"average_ttft":null,"average_latency":49.2157,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-luna-pro","base_model_name":"openrouter/openai/gpt-5.6-luna-pro","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-luna-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":210.0261,"average_ttft":5.9547,"average_latency":3.6935,"uptime_percent":100,"cache_hit_percentage":10.1569},"throughput":{"average_tps":210.0261,"average_ttft":5.9547,"average_latency":3.6935,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-luna-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":0.09999999999999999,"output_cost":0.6,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-luna-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-luna:batch","base_model_name":"","max_context_window":1050000,"input_cost":0.09999999999999999,"output_cost":0.6,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-luna:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-sol","base_model_name":"openrouter/openai/gpt-5.6-sol","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}},"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.5471,"average_ttft":null,"average_latency":1.3145,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.5471,"average_ttft":null,"average_latency":1.3145,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-sol-pro","base_model_name":"openrouter/openai/gpt-5.6-sol-pro","max_context_window":1050000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.4,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-sol-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.8448,"average_ttft":null,"average_latency":2.3499,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.8448,"average_ttft":null,"average_latency":2.3499,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-sol-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-sol-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-sol:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-sol:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-terra","base_model_name":"openrouter/openai/gpt-5.6-terra","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}},"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-terra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.3626,"average_ttft":null,"average_latency":0.7798,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.3626,"average_ttft":null,"average_latency":0.7798,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-terra-pro","base_model_name":"openrouter/openai/gpt-5.6-terra-pro","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-terra-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.3468,"average_ttft":null,"average_latency":2.7212,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.3468,"average_ttft":null,"average_latency":2.7212,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-terra-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":6,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-terra-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-5.6-terra:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":6,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-09"},"id":"openrouter/openai/gpt-5.6-terra:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-astra","base_model_name":"","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7698044042186275,"ci_lo":0.7124964807371247,"model":"gpt-6-astra","config":"mini_swe_agent_gpt_6_astra_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02865396174075141,"harness":"mini-swe-agent","version":"v1.1","n_passed":335,"provider":"openai","ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":335,"pass_at_1":0.7411504424778761,"pass_at_4":0.8053097345132744,"pass_rate":0.7411504424778761,"cost_basis":"Current pricing at all context lengths: $10/M uncached input, $12.50/M cache writes, $1/M cache reads, $50/M output; no separate compute-unit fee.","n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.429117203539823,"n_tasks_in_set":113,"median_cost_usd":3.8406789999999997,"mean_agent_steps":28.754424778761063,"reasoning_effort":"xhigh","mean_cache_tokens":1326921.6836283186,"mean_input_tokens":1456927.0929203539,"n_tasks_attempted":113,"mean_compute_units":752203.0973451327,"mean_output_tokens":29557.327433628318,"median_agent_steps":26,"n_tasks_passed_any":91,"median_input_tokens":1163918.5,"completed_by_attempt":[113,113,113,113],"median_compute_units":662371.5,"median_output_tokens":28542.5,"pass_rate_by_attempt":[0.7079646017699115,0.7345132743362832,0.7787610619469026,0.7433628318584071],"mean_duration_seconds":1132.4004424778761,"mean_reasoning_tokens":11255.66592920354,"mean_cache_read_tokens":1326921.6836283186,"mean_cache_write_tokens":129710.02212389381,"median_duration_seconds":959,"median_reasoning_tokens":10434,"median_cache_read_tokens":1035975,"median_cache_write_tokens":103995,"mean_uncached_input_tokens":295.3871681415929,"median_peak_context_tokens":null,"median_output_tokens_to_pass":28361,"median_uncached_input_tokens":87}},"release_date":"2026-09-04"},"id":"openrouter/openai/gpt-6-astra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":14.6785,"average_ttft":null,"average_latency":117.4498,"uptime_percent":100,"cache_hit_percentage":66.608},"throughput":{"average_tps":14.6785,"average_ttft":null,"average_latency":0.1174498,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-astra-pro","base_model_name":"","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-04"},"id":"openrouter/openai/gpt-6-astra-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":31.8294,"average_ttft":null,"average_latency":134.5599,"uptime_percent":83.3333,"cache_hit_percentage":37.2969},"throughput":{"average_tps":31.8294,"average_ttft":null,"average_latency":0.1345599,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-astra-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-04"},"id":"openrouter/openai/gpt-6-astra-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-astra:batch","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-04"},"id":"openrouter/openai/gpt-6-astra:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-luna","base_model_name":"","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-luna","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-luna-pro","base_model_name":"","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-luna-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-luna-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":0.05,"output_cost":0.25,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0.0625,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-luna-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-luna:batch","base_model_name":"","max_context_window":1050000,"input_cost":0.05,"output_cost":0.25,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0.0625,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-luna:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-sol","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-sol-pro","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-sol-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-sol-pro:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-sol-pro:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6-sol:batch","base_model_name":"","max_context_window":1050000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-22"},"id":"openrouter/openai/gpt-6-sol:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6.1-sol","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"openrouter/openai/gpt-6.1-sol","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-6.1-sol-pro","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"openrouter/openai/gpt-6.1-sol-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-audio","base_model_name":"","max_context_window":128000,"input_cost":2.5,"output_cost":10,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-19"},"id":"openrouter/openai/gpt-audio","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-audio-mini","base_model_name":"","max_context_window":128000,"input_cost":0.6,"output_cost":2.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-19"},"id":"openrouter/openai/gpt-audio-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-chat-latest","base_model_name":"openrouter/openai/gpt-chat-latest","max_context_window":400000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-05"},"id":"openrouter/openai/gpt-chat-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.6567,"average_ttft":null,"average_latency":1.2735,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.6567,"average_ttft":null,"average_latency":1.2735,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-oss-120b","base_model_name":"openrouter/openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.037,"output_cost":0.17,"cache_hit_input_cost":0.075,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/openai/gpt-oss-120b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131000,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":67.2998,"average_ttft":null,"average_latency":0.8536,"uptime_percent":100,"cache_hit_percentage":52.0325},"throughput":{"average_tps":67.2998,"average_ttft":null,"average_latency":0.8536,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-oss-120b:batch","base_model_name":"","max_context_window":131072,"input_cost":0.0296,"output_cost":0.136,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"openrouter/openai/gpt-oss-120b:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"reasoning":{"name":"reasoning","type":"object","required":false,"description":"The reasoning for the answer."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-oss-20b","base_model_name":"openrouter/openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.018,"output_cost":0.09,"cache_hit_input_cost":0.009,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/openai/gpt-oss-20b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131000,"release_date":"2025-08-05","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":1,"metrics":{"average_tps":66.1583,"average_ttft":null,"average_latency":25.9956,"uptime_percent":100,"cache_hit_percentage":0.1063},"throughput":{"average_tps":66.1583,"average_ttft":null,"average_latency":25.9956,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-oss-20b:batch","base_model_name":"","max_context_window":131072,"input_cost":0.024,"output_cost":0.112,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"openrouter/openai/gpt-oss-20b:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/gpt-oss-safeguard-20b","base_model_name":"openrouter/openai/gpt-oss-safeguard-20b","max_context_window":131072,"input_cost":0.075,"output_cost":0.3,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-10-29","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/gpt-oss-safeguard-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":140.3727,"average_ttft":null,"average_latency":0.4221,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":140.3727,"average_ttft":null,"average_latency":0.4221,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o1","base_model_name":"openrouter/openai/o1","max_context_window":200000,"input_cost":15,"output_cost":60,"cache_hit_input_cost":7.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/openai/o1"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2024-12-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":16.0364,"average_ttft":null,"average_latency":1.2808,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.0364,"average_ttft":null,"average_latency":1.2808,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"openrouter/openai/o1-pro","base_model_name":"openai/o1-pro","max_context_window":200000,"input_cost":150,"output_cost":600,"cache_hit_input_cost":15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-19"},"id":"openrouter/openai/o1-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":1.4981,"average_ttft":null,"average_latency":13.8305,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":1.4981,"average_ttft":null,"average_latency":13.8305,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3","base_model_name":"openrouter/openai/o3","max_context_window":200000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":0.5,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":40.8796,"average_ttft":null,"average_latency":0.8368,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":40.8796,"average_ttft":null,"average_latency":0.8368,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3-mini","base_model_name":"openrouter/openai/o3-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.55,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-01-31","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o3-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":62.316,"average_ttft":null,"average_latency":1.051,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":62.316,"average_ttft":null,"average_latency":1.051,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3-mini-high","base_model_name":"openrouter/openai/o3-mini-high","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.55,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-02-12","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o3-mini-high","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":56.9492,"average_ttft":null,"average_latency":1.1286,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.9492,"average_ttft":null,"average_latency":1.1286,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3-mini:batch","base_model_name":"","max_context_window":200000,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":0.275,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-31"},"id":"openrouter/openai/o3-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3-pro","base_model_name":"openrouter/openai/o3-pro","max_context_window":200000,"input_cost":20,"output_cost":80,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-06-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o3-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.5942,"average_ttft":null,"average_latency":3.8528,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.5942,"average_ttft":null,"average_latency":3.8528,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o3:batch","base_model_name":"","max_context_window":200000,"input_cost":1,"output_cost":4,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-16"},"id":"openrouter/openai/o3:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o4-mini","base_model_name":"openrouter/openai/o4-mini","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.275,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o4-mini","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":37.5207,"average_ttft":null,"average_latency":1.1713,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.5207,"average_ttft":null,"average_latency":1.1713,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o4-mini-high","base_model_name":"openrouter/openai/o4-mini-high","max_context_window":200000,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.275,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-04-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/openai/o4-mini-high","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":43.9906,"average_ttft":null,"average_latency":1.5319,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":43.9906,"average_ttft":null,"average_latency":1.5319,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openai/o4-mini:batch","base_model_name":"","max_context_window":200000,"input_cost":0.55,"output_cost":2.2,"cache_hit_input_cost":0.1375,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-16"},"id":"openrouter/openai/o4-mini:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openrouter/bodybuilder","base_model_name":"openrouter/openrouter/bodybuilder","max_context_window":128000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-05"},"id":"openrouter/openrouter/bodybuilder","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":28.8612,"average_ttft":null,"average_latency":2.4254,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":28.8612,"average_ttft":null,"average_latency":2.4254,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openrouter/fusion","base_model_name":"","max_context_window":1000000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-13"},"id":"openrouter/openrouter/fusion","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.919,"average_ttft":null,"average_latency":2.2392,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.919,"average_ttft":null,"average_latency":2.2392,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/openrouter/pareto-code","base_model_name":"","max_context_window":2000000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-21"},"id":"openrouter/openrouter/pareto-code","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.5617,"average_ttft":null,"average_latency":3.9319,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.5617,"average_ttft":null,"average_latency":3.9319,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perceptron/perceptron-mk1","base_model_name":"","max_context_window":32768,"input_cost":0.15,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-12"},"id":"openrouter/perceptron/perceptron-mk1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.95,"average_ttft":null,"average_latency":5.096,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.95,"average_ttft":null,"average_latency":5.096,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perceptron/perceptron-mk1.5","base_model_name":"","max_context_window":36864,"input_cost":0.15,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"openrouter/perceptron/perceptron-mk1.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perplexity/sonar","base_model_name":"","max_context_window":127072,"input_cost":1,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":127072,"release_date":"2025-01-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/perplexity/sonar","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.951,"average_ttft":null,"average_latency":0.9046,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.951,"average_ttft":null,"average_latency":0.9046,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perplexity/sonar-deep-research","base_model_name":"","max_context_window":128000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-03-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/perplexity/sonar-deep-research","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perplexity/sonar-pro","base_model_name":"","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-03-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/perplexity/sonar-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":35.1818,"average_ttft":null,"average_latency":2.256,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.1818,"average_ttft":null,"average_latency":2.256,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perplexity/sonar-pro-search","base_model_name":"","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-10-30","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/perplexity/sonar-pro-search","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":29.0827,"average_ttft":null,"average_latency":1.0408,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":29.0827,"average_ttft":null,"average_latency":1.0408,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/perplexity/sonar-reasoning-pro","base_model_name":"","max_context_window":128000,"input_cost":2,"output_cost":8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-03-07","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/perplexity/sonar-reasoning-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.4671,"average_ttft":null,"average_latency":2.0355,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.4671,"average_ttft":null,"average_latency":2.0355,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/poolside/laguna-s-2.1","base_model_name":"","max_context_window":1048576,"input_cost":0.09,"output_cost":0.18,"cache_hit_input_cost":0.009,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-21"},"id":"openrouter/poolside/laguna-s-2.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":50.4668,"average_ttft":null,"average_latency":0.4263,"uptime_percent":100,"cache_hit_percentage":71.1111},"throughput":{"average_tps":50.4668,"average_ttft":null,"average_latency":0.4263,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/poolside/laguna-xs-2.1","base_model_name":"","max_context_window":262144,"input_cost":0.06,"output_cost":0.12,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-02"},"id":"openrouter/poolside/laguna-xs-2.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":137.1005,"average_ttft":null,"average_latency":0.4677,"uptime_percent":100,"cache_hit_percentage":71.1111},"throughput":{"average_tps":137.1005,"average_ttft":null,"average_latency":0.4677,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/prism-ml/ternary-bonsai-2-27b","base_model_name":"","max_context_window":262144,"input_cost":0.075,"output_cost":0.5,"cache_hit_input_cost":0.0375,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-18"},"id":"openrouter/prism-ml/ternary-bonsai-2-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.2207,"average_ttft":null,"average_latency":7.177,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.2207,"average_ttft":null,"average_latency":7.177,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen-2.5-72b-instruct","base_model_name":"","max_context_window":32768,"input_cost":0.36,"output_cost":0.39999999999999997,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/qwen/qwen-2.5-72b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-09-19","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen-2.5-72b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":4.1529,"average_ttft":null,"average_latency":27.2434,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":4.1529,"average_ttft":null,"average_latency":27.2434,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen-2.5-7b-instruct","base_model_name":"","max_context_window":32768,"input_cost":0.09999999999999999,"output_cost":0.19999999999999998,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-10-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen-2.5-7b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.5777,"average_ttft":null,"average_latency":0.3074,"uptime_percent":100,"cache_hit_percentage":88.3333},"throughput":{"average_tps":32.5777,"average_ttft":null,"average_latency":0.3074,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen-2.5-coder-32b-instruct","base_model_name":"","max_context_window":32768,"input_cost":0.66,"output_cost":1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["openrouter/qwen/qwen-2.5-coder-32b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2024-11-11","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen-2.5-coder-32b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.184,"average_ttft":null,"average_latency":0.6309,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.184,"average_ttft":null,"average_latency":0.6309,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.26,"output_cost":0.78,"cache_hit_input_cost":0.052,"cache_creation_input_cost":0.325,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-02-01","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.2013,"average_ttft":null,"average_latency":0.6795,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.2013,"average_ttft":null,"average_latency":0.6795,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen-plus-2025-07-28","base_model_name":"","max_context_window":1000000,"input_cost":0.26,"output_cost":0.78,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-09-08","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen-plus-2025-07-28","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.0346,"average_ttft":null,"average_latency":0.8321,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.0346,"average_ttft":null,"average_latency":0.8321,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen2.5-vl-72b-instruct","base_model_name":"","max_context_window":128000,"input_cost":0.7999999999999999,"output_cost":1,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["openrouter/qwen/qwen2.5-vl-72b-instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-02-01","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen2.5-vl-72b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.1811,"average_ttft":null,"average_latency":0.8125,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.1811,"average_ttft":null,"average_latency":0.8125,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-14b","base_model_name":"","max_context_window":131072,"input_cost":0.12,"output_cost":0.24,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131702,"release_date":"2025-04-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-14b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":56.2841,"average_ttft":null,"average_latency":1.1371,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.2841,"average_ttft":null,"average_latency":1.1371,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-235b-a22b","base_model_name":"","max_context_window":131072,"input_cost":0.45499999999999996,"output_cost":1.8199999999999998,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-04-28","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-235b-a22b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":36.0071,"average_ttft":null,"average_latency":1.6127,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.0071,"average_ttft":null,"average_latency":1.6127,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-235b-a22b-2507","base_model_name":"","max_context_window":262144,"input_cost":0.0875,"output_cost":0.35,"cache_hit_input_cost":0.0175,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-07-21","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-235b-a22b-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.8672,"average_ttft":null,"average_latency":1.1673,"uptime_percent":100,"cache_hit_percentage":16.6667},"throughput":{"average_tps":13.8672,"average_ttft":null,"average_latency":1.1673,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-235b-a22b-thinking-2507","base_model_name":"","max_context_window":131072,"input_cost":0.22999999999999998,"output_cost":2.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-07-25","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-235b-a22b-thinking-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":42.5697,"average_ttft":null,"average_latency":1.1737,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.5697,"average_ttft":null,"average_latency":1.1737,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-30b-a3b","base_model_name":"","max_context_window":131072,"input_cost":0.12,"output_cost":0.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-04-28","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-30b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":98.1759,"average_ttft":null,"average_latency":2.4055,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":98.1759,"average_ttft":null,"average_latency":2.4055,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-30b-a3b-instruct-2507","base_model_name":"","max_context_window":262144,"input_cost":0.04815,"output_cost":0.19305,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-07-29","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-30b-a3b-instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.7383,"average_ttft":null,"average_latency":1.0437,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.7383,"average_ttft":null,"average_latency":1.0437,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-30b-a3b-thinking-2507","base_model_name":"","max_context_window":81920,"input_cost":0.19999999999999998,"output_cost":2.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-28","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-30b-a3b-thinking-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":129.8438,"average_ttft":null,"average_latency":2.7804,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":129.8438,"average_ttft":null,"average_latency":2.7804,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-32b","base_model_name":"","max_context_window":131072,"input_cost":0.08,"output_cost":0.28,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-04-28","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-32b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":15.7226,"average_ttft":null,"average_latency":21.0588,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.7226,"average_ttft":null,"average_latency":21.0588,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-8b","base_model_name":"","max_context_window":131072,"input_cost":0.117,"output_cost":0.45499999999999996,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-04-28","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":50.8227,"average_ttft":null,"average_latency":1.8502,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":50.8227,"average_ttft":null,"average_latency":1.8502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-coder","base_model_name":"","max_context_window":262144,"input_cost":0.3,"output_cost":1,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-07-23","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-coder","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.377,"average_ttft":null,"average_latency":1.3773,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.377,"average_ttft":null,"average_latency":1.3773,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-coder-30b-a3b-instruct","base_model_name":"","max_context_window":262144,"input_cost":0.07,"output_cost":0.28,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":160000,"release_date":"2025-07-31","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-coder-30b-a3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.8497,"average_ttft":null,"average_latency":1.1561,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.8497,"average_ttft":null,"average_latency":1.1561,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-coder-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.195,"output_cost":0.975,"cache_hit_input_cost":0.039,"cache_creation_input_cost":0.24375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-09-17","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-coder-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.2007,"average_ttft":null,"average_latency":1.3687,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.2007,"average_ttft":null,"average_latency":1.3687,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-coder-next","base_model_name":"","max_context_window":262144,"input_cost":0.12,"output_cost":0.7999999999999999,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-04","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-coder-next","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.7962,"average_ttft":null,"average_latency":0.8862,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.7962,"average_ttft":null,"average_latency":0.8862,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-coder-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.65,"output_cost":3.25,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0.8125,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2025-09-23","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-coder-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.2582,"average_ttft":null,"average_latency":1.1388,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.2582,"average_ttft":null,"average_latency":1.1388,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-max","base_model_name":"","max_context_window":262144,"input_cost":0.78,"output_cost":3.9,"cache_hit_input_cost":0.156,"cache_creation_input_cost":0.975,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-09-23","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.2052,"average_ttft":null,"average_latency":1.6362,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.2052,"average_ttft":null,"average_latency":1.6362,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-max-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.78,"output_cost":3.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-09","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-max-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.8029,"average_ttft":null,"average_latency":1.0183,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.8029,"average_ttft":null,"average_latency":1.0183,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-next-80b-a3b-instruct","base_model_name":"","max_context_window":262144,"input_cost":0.1,"output_cost":1.1,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-09-11","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-next-80b-a3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":40.2172,"average_ttft":null,"average_latency":0.777,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":40.2172,"average_ttft":null,"average_latency":0.777,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-next-80b-a3b-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2025-09-11","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3-next-80b-a3b-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":107.7461,"average_ttft":null,"average_latency":1.2912,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":107.7461,"average_ttft":null,"average_latency":1.2912,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-235b-a22b-instruct","base_model_name":"","max_context_window":262144,"input_cost":0.21,"output_cost":1.9,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-23"},"id":"openrouter/qwen/qwen3-vl-235b-a22b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":35.086,"average_ttft":null,"average_latency":0.9703,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.086,"average_ttft":null,"average_latency":0.9703,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-235b-a22b-thinking","base_model_name":"","max_context_window":131072,"input_cost":0.39999999999999997,"output_cost":4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-23","expiration_date":"2026-10-09"},"id":"openrouter/qwen/qwen3-vl-235b-a22b-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":51.3694,"average_ttft":null,"average_latency":2.7142,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":51.3694,"average_ttft":null,"average_latency":2.7142,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-30b-a3b-instruct","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-06"},"id":"openrouter/qwen/qwen3-vl-30b-a3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.8959,"average_ttft":null,"average_latency":0.5745,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.8959,"average_ttft":null,"average_latency":0.5745,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-30b-a3b-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.19999999999999998,"output_cost":2.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-06","expiration_date":"2026-10-09"},"id":"openrouter/qwen/qwen3-vl-30b-a3b-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":56.8787,"average_ttft":null,"average_latency":4.3532,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.8787,"average_ttft":null,"average_latency":4.3532,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-32b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.10400000000000001,"output_cost":0.41600000000000004,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-23","expiration_date":"2026-10-09"},"id":"openrouter/qwen/qwen3-vl-32b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.7934,"average_ttft":null,"average_latency":0.8558,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.7934,"average_ttft":null,"average_latency":0.8558,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-8b-instruct","base_model_name":"","max_context_window":262144,"input_cost":0.117,"output_cost":0.45499999999999996,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-14","expiration_date":"2026-10-09"},"id":"openrouter/qwen/qwen3-vl-8b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.7538,"average_ttft":null,"average_latency":0.5055,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.7538,"average_ttft":null,"average_latency":0.5055,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3-vl-8b-thinking","base_model_name":"","max_context_window":131072,"input_cost":0.18,"output_cost":2.0999999999999996,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-14","expiration_date":"2026-10-09"},"id":"openrouter/qwen/qwen3-vl-8b-thinking","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":111.7808,"average_ttft":null,"average_latency":2.2388,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":111.7808,"average_ttft":null,"average_latency":2.2388,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-122b-a10b","base_model_name":"","max_context_window":262144,"input_cost":0.26,"output_cost":2.08,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-122b-a10b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":141.0183,"average_ttft":null,"average_latency":1.9733,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":141.0183,"average_ttft":null,"average_latency":1.9733,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-27b","base_model_name":"","max_context_window":262144,"input_cost":0.195,"output_cost":1.56,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":58.6526,"average_ttft":null,"average_latency":9.7244,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":58.6526,"average_ttft":null,"average_latency":9.7244,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-35b-a3b","base_model_name":"","max_context_window":262144,"input_cost":0.1625,"output_cost":1.3,"cache_hit_input_cost":0.15625,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":85.2045,"average_ttft":null,"average_latency":0.7516,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":85.2045,"average_ttft":null,"average_latency":0.7516,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-397b-a17b","base_model_name":"","max_context_window":262144,"input_cost":0.55,"output_cost":3.5,"cache_hit_input_cost":0.225,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-02-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-397b-a17b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":77.2198,"average_ttft":null,"average_latency":64.8038,"uptime_percent":100,"cache_hit_percentage":67.9489},"throughput":{"average_tps":77.2198,"average_ttft":null,"average_latency":64.8038,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-9b","base_model_name":"","max_context_window":262144,"input_cost":0.09999999999999999,"output_cost":0.15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-03-10","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-9b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":40.8523,"average_ttft":null,"average_latency":15.2077,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":40.8523,"average_ttft":null,"average_latency":15.2077,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-flash-02-23","base_model_name":"","max_context_window":1000000,"input_cost":0.065,"output_cost":0.26,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-02-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-flash-02-23","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":82.2765,"average_ttft":null,"average_latency":0.7815,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":82.2765,"average_ttft":null,"average_latency":0.7815,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-plus-02-15","base_model_name":"","max_context_window":1000000,"input_cost":0.26,"output_cost":1.56,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-02-16","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-plus-02-15","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.6486,"average_ttft":null,"average_latency":2.1557,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.6486,"average_ttft":null,"average_latency":2.1557,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.5-plus-20260420","base_model_name":"","max_context_window":1000000,"input_cost":0.3,"output_cost":1.7999999999999998,"cache_hit_input_cost":0,"cache_creation_input_cost":0.375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.5-plus-20260420","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.3289,"average_ttft":null,"average_latency":4.2902,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.3289,"average_ttft":null,"average_latency":4.2902,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.6-27b","base_model_name":"","max_context_window":262144,"input_cost":0.32,"output_cost":3.2,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.6-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":38.8501,"average_ttft":null,"average_latency":3.4056,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.8501,"average_ttft":null,"average_latency":3.4056,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.6-35b-a3b","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":1,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.6-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":73.8612,"average_ttft":null,"average_latency":0.8716,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":73.8612,"average_ttft":null,"average_latency":0.8716,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.6-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.1875,"output_cost":1.125,"cache_hit_input_cost":0,"cache_creation_input_cost":0.234375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-27","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":52.6288,"average_ttft":null,"average_latency":1.2606,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":52.6288,"average_ttft":null,"average_latency":1.2606,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.6-max-preview","base_model_name":"","max_context_window":262144,"input_cost":1.0270000000000001,"output_cost":6.162,"cache_hit_input_cost":0,"cache_creation_input_cost":1.28375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":262144,"release_date":"2026-04-27","prompt_logging":false,"expiration_date":"2026-10-09","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.6-max-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":43.3755,"average_ttft":null,"average_latency":6.4666,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":43.3755,"average_ttft":null,"average_latency":6.4666,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.6-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.325,"output_cost":1.95,"cache_hit_input_cost":0,"cache_creation_input_cost":0.40625,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-02","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.6-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":33.7347,"average_ttft":null,"average_latency":1.9741,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":33.7347,"average_ttft":null,"average_latency":1.9741,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.7-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.03,"output_cost":0.13,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0.038,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-27"},"id":"openrouter/qwen/qwen3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":38.0477,"average_ttft":null,"average_latency":1.6824,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.0477,"average_ttft":null,"average_latency":1.6824,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.7-max","base_model_name":"","max_context_window":1000000,"input_cost":1.475,"output_cost":4.425,"cache_hit_input_cost":0.295,"cache_creation_input_cost":1.84375,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-05-21","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.7-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":47.6021,"average_ttft":null,"average_latency":1.3453,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":47.6021,"average_ttft":null,"average_latency":1.3453,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.7-plus","base_model_name":"","max_context_window":1000000,"input_cost":0.32,"output_cost":1.28,"cache_hit_input_cost":0.064,"cache_creation_input_cost":0.4,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-06-03","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/qwen/qwen3.7-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":36.9649,"average_ttft":null,"average_latency":1.7335,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.9649,"average_ttft":null,"average_latency":1.7335,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-2.4t-a95b","base_model_name":"","max_context_window":1048576,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-12"},"id":"openrouter/qwen/qwen3.8-2.4t-a95b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":38.1374,"average_ttft":null,"average_latency":1.4758,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.1374,"average_ttft":null,"average_latency":1.4758,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-27b","base_model_name":"","max_context_window":1000000,"input_cost":0.42,"output_cost":3,"cache_hit_input_cost":0.085,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-14"},"id":"openrouter/qwen/qwen3.8-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":35.7845,"average_ttft":null,"average_latency":1.0288,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.7845,"average_ttft":null,"average_latency":1.0288,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.15,"output_cost":0.47,"cache_hit_input_cost":0.016,"cache_creation_input_cost":0.2,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-26"},"id":"openrouter/qwen/qwen3.8-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.1744,"average_ttft":null,"average_latency":1.6502,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.1744,"average_ttft":null,"average_latency":1.6502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-max-0902","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-09-03"},"id":"openrouter/qwen/qwen3.8-max-0902","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.6768,"average_ttft":null,"average_latency":2.0524,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.6768,"average_ttft":null,"average_latency":2.0524,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-max-prime","base_model_name":"","max_context_window":1000000,"input_cost":4,"output_cost":12,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"openrouter/qwen/qwen3.8-max-prime","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/qwen/qwen3.8-omni-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.15,"output_cost":0.47,"cache_hit_input_cost":0.016,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"openrouter/qwen/qwen3.8-omni-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/rekaai/reka-edge","base_model_name":"","max_context_window":16384,"input_cost":0.09999999999999999,"output_cost":0.09999999999999999,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-20"},"id":"openrouter/rekaai/reka-edge","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":29.025,"average_ttft":null,"average_latency":0.3454,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":29.025,"average_ttft":null,"average_latency":0.3454,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/rekaai/reka-flash-3","base_model_name":"","max_context_window":65536,"input_cost":0.09999999999999999,"output_cost":0.19999999999999998,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-12"},"id":"openrouter/rekaai/reka-flash-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":71.8935,"average_ttft":null,"average_latency":0.8908,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":71.8935,"average_ttft":null,"average_latency":0.8908,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/relace/relace-apply-3","base_model_name":"","max_context_window":256000,"input_cost":0.85,"output_cost":1.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-26"},"id":"openrouter/relace/relace-apply-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/relace/relace-search","base_model_name":"","max_context_window":256000,"input_cost":1,"output_cost":3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-08"},"id":"openrouter/relace/relace-search","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.1093,"average_ttft":null,"average_latency":0.3277,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.1093,"average_ttft":null,"average_latency":0.3277,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sakana/fugu-max","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/sakana/fugu-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":25.7436,"average_ttft":null,"average_latency":2.5578,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.7436,"average_ttft":null,"average_latency":2.5578,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sakana/fugu-ultra","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-24"},"id":"openrouter/sakana/fugu-ultra","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.5001,"average_ttft":null,"average_latency":5.4238,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":5.5001,"average_ttft":null,"average_latency":5.4238,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sakana/fugu-ultra-v2","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-11"},"id":"openrouter/sakana/fugu-ultra-v2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":11.3287,"average_ttft":null,"average_latency":4.9106,"uptime_percent":100,"cache_hit_percentage":38.7022},"throughput":{"average_tps":11.3287,"average_ttft":null,"average_latency":4.9106,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sakana/sakana-namazu","base_model_name":"","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-11"},"id":"openrouter/sakana/sakana-namazu","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sao10k/l3-lunaris-8b","base_model_name":"","max_context_window":8192,"input_cost":0.04,"output_cost":0.049999999999999996,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-08-13"},"id":"openrouter/sao10k/l3-lunaris-8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":61.7169,"average_ttft":null,"average_latency":0.5257,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":61.7169,"average_ttft":null,"average_latency":0.5257,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sao10k/l3.1-euryale-70b","base_model_name":"","max_context_window":131072,"input_cost":0.85,"output_cost":0.85,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-08-28"},"id":"openrouter/sao10k/l3.1-euryale-70b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.2242,"average_ttft":null,"average_latency":0.8291,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.2242,"average_ttft":null,"average_latency":0.8291,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/sao10k/l3.3-euryale-70b","base_model_name":"","max_context_window":131072,"input_cost":0.65,"output_cost":0.75,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-18"},"id":"openrouter/sao10k/l3.3-euryale-70b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.2854,"average_ttft":null,"average_latency":2.2832,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.2854,"average_ttft":null,"average_latency":2.2832,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/stepfun/step-3.5-flash","base_model_name":"","max_context_window":262144,"input_cost":0.09999999999999999,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-29"},"id":"openrouter/stepfun/step-3.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.7302,"average_ttft":null,"average_latency":2.017,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.7302,"average_ttft":null,"average_latency":2.017,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/stepfun/step-3.7-flash","base_model_name":"","max_context_window":262144,"input_cost":0.19999999999999998,"output_cost":1.15,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-28"},"id":"openrouter/stepfun/step-3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":74.5754,"average_ttft":null,"average_latency":1.4647,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":74.5754,"average_ttft":null,"average_latency":1.4647,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hunyuan-a13b-instruct","base_model_name":"","max_context_window":131072,"input_cost":0.14,"output_cost":0.5700000000000001,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-08"},"id":"openrouter/tencent/hunyuan-a13b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.2354,"average_ttft":null,"average_latency":2.7025,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":22.2354,"average_ttft":null,"average_latency":2.7025,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy-mt2-1.8b","base_model_name":"","max_context_window":8192,"input_cost":0.044,"output_cost":0.17700000000000002,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-20"},"id":"openrouter/tencent/hy-mt2-1.8b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.9656,"average_ttft":null,"average_latency":0.8399,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":11.9656,"average_ttft":null,"average_latency":0.8399,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy-mt2-30b-a3b","base_model_name":"","max_context_window":8192,"input_cost":0.074,"output_cost":0.295,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-20"},"id":"openrouter/tencent/hy-mt2-30b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":10.1404,"average_ttft":null,"average_latency":1.0935,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":10.1404,"average_ttft":null,"average_latency":1.0935,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy-mt2-7b","base_model_name":"","max_context_window":8192,"input_cost":0.074,"output_cost":0.295,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-19"},"id":"openrouter/tencent/hy-mt2-7b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.6884,"average_ttft":null,"average_latency":0.9535,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.6884,"average_ttft":null,"average_latency":0.9535,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy3","base_model_name":"","max_context_window":262144,"input_cost":0.132,"output_cost":0.528,"cache_hit_input_cost":0.033,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-06"},"id":"openrouter/tencent/hy3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.8596,"average_ttft":null,"average_latency":4.4742,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.8596,"average_ttft":null,"average_latency":4.4742,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy3-preview","base_model_name":"","max_context_window":262144,"input_cost":0.18,"output_cost":0.6,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"openrouter/tencent/hy3-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.0159,"average_ttft":null,"average_latency":2.3139,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.0159,"average_ttft":null,"average_latency":2.3139,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/tencent/hy4-preview","base_model_name":"","max_context_window":1048576,"input_cost":0.834,"output_cost":2.501,"cache_hit_input_cost":0.042,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-28"},"id":"openrouter/tencent/hy4-preview","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.9758,"average_ttft":null,"average_latency":3.373,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.9758,"average_ttft":null,"average_latency":3.373,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/thedrummer/cydonia-24b-v4.1","base_model_name":"","max_context_window":131072,"input_cost":0.3,"output_cost":0.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-27"},"id":"openrouter/thedrummer/cydonia-24b-v4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":12.4905,"average_ttft":null,"average_latency":1.5478,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.4905,"average_ttft":null,"average_latency":1.5478,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/thedrummer/skyfall-36b-v2","base_model_name":"","max_context_window":32768,"input_cost":0.55,"output_cost":0.7999999999999999,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-10"},"id":"openrouter/thedrummer/skyfall-36b-v2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":41.3559,"average_ttft":null,"average_latency":0.6074,"uptime_percent":100,"cache_hit_percentage":98.8764},"throughput":{"average_tps":41.3559,"average_ttft":null,"average_latency":0.6074,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/thedrummer/unslopnemo-12b","base_model_name":"","max_context_window":1024000,"input_cost":0.39999999999999997,"output_cost":0.39999999999999997,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-11-08"},"id":"openrouter/thedrummer/unslopnemo-12b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":32.9657,"average_ttft":null,"average_latency":0.5796,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.9657,"average_ttft":null,"average_latency":0.5796,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/thinkingmachines/inkling","base_model_name":"","max_context_window":524288,"input_cost":1,"output_cost":4.05,"cache_hit_input_cost":0.17,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-17"},"id":"openrouter/thinkingmachines/inkling","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":76.0094,"average_ttft":null,"average_latency":1.2427,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":76.0094,"average_ttft":null,"average_latency":1.2427,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/thinkingmachines/inkling-small","base_model_name":"","max_context_window":524288,"input_cost":0.44999999999999996,"output_cost":1.2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-07-30"},"id":"openrouter/thinkingmachines/inkling-small","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":37.7946,"average_ttft":null,"average_latency":119.4774,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.7946,"average_ttft":null,"average_latency":0.1194774,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/unbiased/pareto","base_model_name":"","max_context_window":262144,"input_cost":2.5,"output_cost":7.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-17"},"id":"openrouter/unbiased/pareto","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.148,"average_ttft":null,"average_latency":1.2936,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.148,"average_ttft":null,"average_latency":1.2936,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/undi95/remm-slerp-l2-13b","base_model_name":"","max_context_window":6144,"input_cost":0.35,"output_cost":0.65,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-07-22"},"id":"openrouter/undi95/remm-slerp-l2-13b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.8722,"average_ttft":null,"average_latency":0.4577,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.8722,"average_ttft":null,"average_latency":0.4577,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/upstage/solar-mini4","base_model_name":"","max_context_window":524288,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"openrouter/upstage/solar-mini4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/upstage/solar-pro-3","base_model_name":"","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-27"},"id":"openrouter/upstage/solar-pro-3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.936,"average_ttft":null,"average_latency":1.235,"uptime_percent":100,"cache_hit_percentage":91.4286},"throughput":{"average_tps":8.936,"average_ttft":null,"average_latency":1.235,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/upstage/solar-pro4","base_model_name":"","max_context_window":524288,"input_cost":0.09,"output_cost":0.36,"cache_hit_input_cost":0.018,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-10"},"id":"openrouter/upstage/solar-pro4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.4006,"average_ttft":null,"average_latency":0.7832,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.4006,"average_ttft":null,"average_latency":0.7832,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/writer/palmyra-x5","base_model_name":"","max_context_window":1040000,"input_cost":0.6,"output_cost":6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-21"},"id":"openrouter/writer/palmyra-x5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":48.3541,"average_ttft":null,"average_latency":0.6609,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":48.3541,"average_ttft":null,"average_latency":0.6609,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.20","base_model_name":"","max_context_window":2000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-31"},"id":"openrouter/x-ai/grok-4.20","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.6563,"average_ttft":null,"average_latency":0.4579,"uptime_percent":100,"cache_hit_percentage":69.1892},"throughput":{"average_tps":19.6563,"average_ttft":null,"average_latency":0.4579,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.20-multi-agent","base_model_name":"","max_context_window":2000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-31"},"id":"openrouter/x-ai/grok-4.20-multi-agent","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":434.7784,"average_ttft":null,"average_latency":3.6041,"uptime_percent":100,"cache_hit_percentage":77.6654},"throughput":{"average_tps":434.7784,"average_ttft":null,"average_latency":3.6041,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.3","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-30"},"id":"openrouter/x-ai/grok-4.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":70.2139,"average_ttft":null,"average_latency":1.7586,"uptime_percent":100,"cache_hit_percentage":98.7993},"throughput":{"average_tps":70.2139,"average_ttft":null,"average_latency":1.7586,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.3:batch","base_model_name":"","max_context_window":1000000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-30"},"id":"openrouter/x-ai/grok-4.3:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.5","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5604186651978057,"ci_lo":0.5148025737402474,"model":"grok-4-5","config":"mini_swe_agent_grok_4_5_high","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":243,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":243,"pass_at_1":0.5376106194690266,"pass_at_4":0.7787610619469026,"pass_rate":0.5376106194690266,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.4157481725663716,"n_tasks_in_set":113,"median_cost_usd":2.02311,"mean_agent_steps":61.33185840707964,"reasoning_effort":"high","mean_cache_tokens":3943846.5132743362,"mean_input_tokens":4059182.975663717,"n_tasks_attempted":113,"mean_output_tokens":35525.33185840708,"median_agent_steps":56,"n_tasks_passed_any":88,"median_input_tokens":3293744.5,"median_output_tokens":34250,"mean_duration_seconds":484.7029359800885,"median_duration_seconds":430.0852805,"median_peak_context_tokens":94044,"median_output_tokens_to_pass":33872}},"release_date":"2026-07-08"},"id":"openrouter/x-ai/grok-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":30.3165,"average_ttft":null,"average_latency":1.0228,"uptime_percent":100,"cache_hit_percentage":61.8357},"throughput":{"average_tps":30.3165,"average_ttft":null,"average_latency":1.0228,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.6","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.697586806790726,"ci_lo":0.6519707153331677,"model":"grok-4-6","config":"mini_swe_agent_grok_4_6_medium","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":305,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":305,"pass_at_1":0.6747787610619469,"pass_at_4":0.8407079646017699,"pass_rate":0.6747787610619469,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4489837522123894,"n_tasks_in_set":113,"median_cost_usd":2.945834,"mean_agent_steps":70.28982300884955,"reasoning_effort":"medium","mean_cache_tokens":5533327.0088495575,"mean_input_tokens":5725195.139380531,"n_tasks_attempted":113,"mean_output_tokens":49763.99778761062,"median_agent_steps":66,"n_tasks_passed_any":95,"median_input_tokens":4705124,"median_output_tokens":48585.5,"mean_duration_seconds":895.5380579646018,"median_duration_seconds":860.0352045,"median_peak_context_tokens":116622,"median_output_tokens_to_pass":48346}},"release_date":"2026-08-12"},"id":"openrouter/x-ai/grok-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":52.025,"average_ttft":null,"average_latency":7.1502,"uptime_percent":99.9572,"cache_hit_percentage":64.6686},"throughput":{"average_tps":52.025,"average_ttft":null,"average_latency":7.1502,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-4.7","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"openrouter/x-ai/grok-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/x-ai/grok-build-0.1","base_model_name":"","max_context_window":256000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-20"},"id":"openrouter/x-ai/grok-build-0.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":49.2313,"average_ttft":null,"average_latency":9.6806,"uptime_percent":100,"cache_hit_percentage":68.4492},"throughput":{"average_tps":49.2313,"average_ttft":null,"average_latency":9.6806,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/xiaomi/mimo-v2.5","base_model_name":"","max_context_window":1050000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.0028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"openrouter/xiaomi/mimo-v2.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.0111,"average_ttft":null,"average_latency":3.5568,"uptime_percent":100,"cache_hit_percentage":77.4194},"throughput":{"average_tps":18.0111,"average_ttft":null,"average_latency":3.5568,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/xiaomi/mimo-v2.5-pro","base_model_name":"","max_context_window":1050000,"input_cost":0.435,"output_cost":0.87,"cache_hit_input_cost":0.0036,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-22"},"id":"openrouter/xiaomi/mimo-v2.5-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.3498,"average_ttft":null,"average_latency":1.9871,"uptime_percent":100,"cache_hit_percentage":85.7143},"throughput":{"average_tps":35.3498,"average_ttft":null,"average_latency":1.9871,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/xiaomi/mimo-v2.6-flash","base_model_name":"","max_context_window":1050000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.0028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"openrouter/xiaomi/mimo-v2.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/xiaomi/mimo-v2.6-pro","base_model_name":"","max_context_window":1050000,"input_cost":0.435,"output_cost":0.87,"cache_hit_input_cost":0.0036,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"openrouter/xiaomi/mimo-v2.6-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/xiaomi/mimo-v2.6-pro-ultraspeed","base_model_name":"","max_context_window":1048576,"input_cost":4.35,"output_cost":8.7,"cache_hit_input_cost":0.036,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"openrouter/xiaomi/mimo-v2.6-pro-ultraspeed","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.5","base_model_name":"openrouter/z-ai/glm-4.5","max_context_window":131072,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-07-25","prompt_logging":false,"expiration_date":"2026-12-31","prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.2977,"average_ttft":null,"average_latency":7.7643,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":30.2977,"average_ttft":null,"average_latency":7.7643,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.5-air","base_model_name":"openrouter/z-ai/glm-4.5-air","max_context_window":131072,"input_cost":0.13,"output_cost":0.85,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-07-25","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.5-air","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":40.7668,"average_ttft":null,"average_latency":1.5977,"uptime_percent":100,"cache_hit_percentage":66.6667},"throughput":{"average_tps":40.7668,"average_ttft":null,"average_latency":1.5977,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.5v","base_model_name":"openrouter/z-ai/glm-4.5v","max_context_window":65536,"input_cost":0.6,"output_cost":1.7999999999999998,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":65536,"release_date":"2025-08-11","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.5v","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.0205,"average_ttft":null,"average_latency":7.2033,"uptime_percent":100,"cache_hit_percentage":16.6667},"throughput":{"average_tps":20.0205,"average_ttft":null,"average_latency":7.2033,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.6","base_model_name":"openrouter/z-ai/glm-4.6","max_context_window":204800,"input_cost":0.43,"output_cost":1.75,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":202752,"release_date":"2025-09-30","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":56.3109,"average_ttft":null,"average_latency":1.2359,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":56.3109,"average_ttft":null,"average_latency":1.2359,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.6v","base_model_name":"openrouter/z-ai/glm-4.6v","max_context_window":131072,"input_cost":0.3,"output_cost":0.8999999999999999,"cache_hit_input_cost":0.055,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-12-08","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.6v","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":22.7327,"average_ttft":null,"average_latency":2.8159,"uptime_percent":100,"cache_hit_percentage":57.1429},"throughput":{"average_tps":22.7327,"average_ttft":null,"average_latency":2.8159,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.7","base_model_name":"openrouter/z-ai/glm-4.7","max_context_window":204800,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":202752,"release_date":"2025-12-22","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":17.9527,"average_ttft":null,"average_latency":7.0255,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":17.9527,"average_ttft":null,"average_latency":7.0255,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-4.7-flash","base_model_name":"openrouter/z-ai/glm-4.7-flash","max_context_window":200000,"input_cost":0.060500000000000005,"output_cost":0.39999999999999997,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":202752,"release_date":"2026-01-19","prompt_logging":false,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"openrouter/z-ai/glm-4.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.7687,"average_ttft":null,"average_latency":7.461,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.7687,"average_ttft":null,"average_latency":7.461,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5","base_model_name":"openrouter/z-ai/glm-5","max_context_window":204800,"input_cost":0.6,"output_cost":1.92,"cache_hit_input_cost":0.12,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-11"},"id":"openrouter/z-ai/glm-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.8007,"average_ttft":null,"average_latency":4.6524,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.8007,"average_ttft":null,"average_latency":4.6524,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5-turbo","base_model_name":"openrouter/z-ai/glm-5-turbo","max_context_window":202752,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-15","expiration_date":"2098-12-31"},"id":"openrouter/z-ai/glm-5-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.6733,"average_ttft":null,"average_latency":7.4516,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.6733,"average_ttft":null,"average_latency":7.4516,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.1","base_model_name":"openrouter/z-ai/glm-5.1","max_context_window":204800,"input_cost":0.9646,"output_cost":3.0316,"cache_hit_input_cost":0.17914,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"openrouter/z-ai/glm-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.3748,"average_ttft":null,"average_latency":3.8837,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.3748,"average_ttft":null,"average_latency":3.8837,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.2","base_model_name":"","max_context_window":1048576,"input_cost":1.1,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16"},"id":"openrouter/z-ai/glm-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.1989,"average_ttft":null,"average_latency":2.2378,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.1989,"average_ttft":null,"average_latency":2.2378,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3","base_model_name":"","max_context_window":1048576,"input_cost":0.2219,"output_cost":4.4,"cache_hit_input_cost":0.1775,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18"},"id":"openrouter/z-ai/glm-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":584.1764,"average_ttft":3.391,"average_latency":2.746,"uptime_percent":99.7639,"cache_hit_percentage":90.4655},"throughput":{"average_tps":584.1764,"average_ttft":3.391,"average_latency":2.746,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"openrouter/z-ai/glm-5.3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.2108,"average_ttft":4.8525,"average_latency":8.8,"uptime_percent":99.9977,"cache_hit_percentage":86.5866},"throughput":{"average_tps":18.2108,"average_ttft":4.8525,"average_latency":8.8,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3-flash:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.06,"output_cost":0.2,"cache_hit_input_cost":0.012,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-26"},"id":"openrouter/z-ai/glm-5.3-flash:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3-flashx","base_model_name":"","max_context_window":1048576,"input_cost":0.37,"output_cost":1.25,"cache_hit_input_cost":0.09,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-18","expiration_date":"2098-12-31"},"id":"openrouter/z-ai/glm-5.3-flashx","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3-prime","base_model_name":"","max_context_window":1000000,"input_cost":2.8,"output_cost":8.8,"cache_hit_input_cost":0.56,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"openrouter/z-ai/glm-5.3-prime","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5.3:batch","base_model_name":"","max_context_window":1048576,"input_cost":0.45,"output_cost":2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-18"},"id":"openrouter/z-ai/glm-5.3:batch","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"OpenRouter","provider_id":"openrouter","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.036768Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://openrouter.ai/api/v1/models"},"kind":"host","id":"openrouter"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"openrouter/z-ai/glm-5v-turbo","base_model_name":"openrouter/z-ai/glm-5v-turbo","max_context_window":202752,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-01","expiration_date":"2098-12-31"},"id":"openrouter/z-ai/glm-5v-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.4053,"average_ttft":null,"average_latency":3.8726,"uptime_percent":100,"cache_hit_percentage":33.3333},"throughput":{"average_tps":17.4053,"average_ttft":null,"average_latency":3.8726,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Palm","provider_id":"google_palm","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:50.969343Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"google_palm"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"palm/chat-bison","base_model_name":"palm/chat-bison","max_context_window":8192,"input_cost":0.125,"output_cost":0.125,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["palm/chat-bison"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8192,"release_date":"2023-05-10","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"palm/chat-bison","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/BAAI/bge-m3","base_model_name":"parasail/BAAI/bge-m3","max_context_window":8192,"input_cost":0.01,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"embedding","metadata":{"release_date":"2024-01-30","is_available_on_credits":true},"id":"parasail/BAAI/bge-m3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/ByteDance-Seed/UI-TARS-1.5-7B","base_model_name":"ByteDance-Seed/UI-TARS-1.5-7B","max_context_window":128000,"input_cost":0.1,"output_cost":0.2,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-22"},"id":"parasail/ByteDance-Seed/UI-TARS-1.5-7B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.1559,"average_ttft":null,"average_latency":0.522,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.1559,"average_ttft":null,"average_latency":0.522,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"deepseek-ai/DeepSeek-V4-Flash","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"parasail/deepseek-ai/DeepSeek-V4-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":79.7461,"average_ttft":2.338,"average_latency":10.8917,"uptime_percent":99.9677,"cache_hit_percentage":53.1229},"throughput":{"average_tps":79.7461,"average_ttft":2.338,"average_latency":10.8917,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"parasail/deepseek-ai/DeepSeek-V4-Flash-0731","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-31","is_available_on_credits":true},"id":"parasail/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"deepseek-ai/DeepSeek-V4-Pro","max_context_window":1048576,"input_cost":1.74,"output_cost":3.48,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24"},"id":"parasail/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":49.7009,"average_ttft":null,"average_latency":1.1469,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":49.7009,"average_ttft":null,"average_latency":1.1469,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"parasail/deepseek-ai/DeepSeek-V4-Pro-0813","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-13","is_available_on_credits":true},"id":"parasail/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"parasail/deepseek-ai/DeepSeek-V4.1-Flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10","is_available_on_credits":true},"id":"parasail/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/google/gemma-3-27b-it","base_model_name":"google/gemma-3-27b-it","max_context_window":131072,"input_cost":0.08,"output_cost":0.45,"cache_hit_input_cost":0.008,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["google/gemma-3-27b-it"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-12"},"id":"parasail/google/gemma-3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":39.0149,"average_ttft":null,"average_latency":1.0765,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":39.0149,"average_ttft":null,"average_latency":1.0765,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/google/gemma-4-26B-A4B","base_model_name":"parasail/google/gemma-4-26B-A4B","max_context_window":262144,"input_cost":0.13,"output_cost":0.4,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02","is_available_on_credits":true},"id":"parasail/google/gemma-4-26B-A4B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/google/gemma-4-26B-A4B-it","base_model_name":"google/gemma-4-26B-A4B-it","max_context_window":262144,"input_cost":0.13,"output_cost":0.4,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"parasail/google/gemma-4-26B-A4B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.3797,"average_ttft":1.552,"average_latency":1.9419,"uptime_percent":100,"cache_hit_percentage":16.5387},"throughput":{"average_tps":8.3797,"average_ttft":1.552,"average_latency":1.9419,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/google/gemma-4-31B","base_model_name":"parasail/google/gemma-4-31B","max_context_window":262144,"input_cost":0.15,"output_cost":0.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02","is_available_on_credits":true},"id":"parasail/google/gemma-4-31B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/google/gemma-4-31b-it","base_model_name":"google/gemma-4-31b-it","max_context_window":262144,"input_cost":0.15,"output_cost":0.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"parasail/google/gemma-4-31b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.4862,"average_ttft":null,"average_latency":0.4881,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.4862,"average_ttft":null,"average_latency":0.4881,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/google/gemma-4-31B-it","base_model_name":"google/gemma-4-31B-it","max_context_window":262144,"input_cost":0.15,"output_cost":0.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"parasail/google/gemma-4-31B-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":26.5761,"average_ttft":null,"average_latency":0.3763,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.5761,"average_ttft":null,"average_latency":0.3763,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/meta-llama/Llama-3.2-3B-Instruct","base_model_name":"parasail/meta-llama/Llama-3.2-3B-Instruct","max_context_window":131072,"input_cost":0.05,"output_cost":0.33,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-25","is_available_on_credits":true},"id":"parasail/meta-llama/Llama-3.2-3B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/meta-llama/Llama-3.3-70B-Instruct","base_model_name":"meta-llama/Llama-3.3-70B-Instruct","max_context_window":131072,"input_cost":0.22,"output_cost":0.5,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["meta-llama/Llama-3.3-70B-Instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06"},"id":"parasail/meta-llama/Llama-3.3-70B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":13.7757,"average_ttft":null,"average_latency":0.5991,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.7757,"average_ttft":null,"average_latency":0.5991,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/meta-llama/Llama-4-Maverick-17B-128E-Instruct","base_model_name":"meta-llama/Llama-4-Maverick-17B-128E-Instruct","max_context_window":1048576,"input_cost":0.35,"output_cost":1,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-05"},"id":"parasail/meta-llama/Llama-4-Maverick-17B-128E-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":24.6464,"average_ttft":null,"average_latency":0.6263,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.6464,"average_ttft":null,"average_latency":0.6263,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/MiniMaxAI/Minimax-M3","base_model_name":"parasail/MiniMaxAI/Minimax-M3","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-31","is_available_on_credits":true},"id":"parasail/MiniMaxAI/Minimax-M3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/MiniMaxAI/MiniMax-M3","base_model_name":"parasail/MiniMaxAI/MiniMax-M3","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-31","is_available_on_credits":true},"id":"parasail/MiniMaxAI/MiniMax-M3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/mistralai/Mistral-Nemo-Instruct-2407","base_model_name":"parasail/mistralai/Mistral-Nemo-Instruct-2407","max_context_window":131072,"input_cost":0.03,"output_cost":0.03,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-18","is_available_on_credits":true},"id":"parasail/mistralai/Mistral-Nemo-Instruct-2407","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.247,"average_ttft":null,"average_latency":0.4802,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.247,"average_ttft":null,"average_latency":0.4802,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/mistralai/Mistral-Small-3.2-24B-Instruct-2506","base_model_name":"mistralai/Mistral-Small-3.2-24B-Instruct-2506","max_context_window":128000,"input_cost":0.09,"output_cost":0.6,"cache_hit_input_cost":0.009,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/mistralai/Mistral-Small-3.2-24B-Instruct-2506","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.2477,"average_ttft":null,"average_latency":0.6942,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.2477,"average_ttft":null,"average_latency":0.6942,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/moonshotai/Kimi-K2.6","base_model_name":"moonshotai/Kimi-K2.6","max_context_window":262144,"input_cost":0.75,"output_cost":3.5,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"parasail/moonshotai/Kimi-K2.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":102.2643,"average_ttft":null,"average_latency":11.5195,"uptime_percent":100,"cache_hit_percentage":4.6917},"throughput":{"average_tps":102.2643,"average_ttft":null,"average_latency":11.5195,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/moonshotai/Kimi-K3","base_model_name":"parasail/moonshotai/Kimi-K3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16","is_available_on_credits":true},"id":"parasail/moonshotai/Kimi-K3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.1,"output_cost":0.75,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"parasail/openai/gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":63.0763,"average_ttft":null,"average_latency":0.7166,"uptime_percent":100,"cache_hit_percentage":94.1176},"throughput":{"average_tps":63.0763,"average_ttft":null,"average_latency":0.7166,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/openai/gpt-oss-120b-fast","base_model_name":"parasail/openai/gpt-oss-120b-fast","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05","is_available_on_credits":true},"id":"parasail/openai/gpt-oss-120b-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.04,"output_cost":0.2,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"parasail/openai/gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":19.2939,"average_ttft":null,"average_latency":2.3842,"uptime_percent":100,"cache_hit_percentage":64},"throughput":{"average_tps":19.2939,"average_ttft":null,"average_latency":2.3842,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-bge-m3","base_model_name":"parasail/parasail-bge-m3","max_context_window":8192,"input_cost":0.01,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"embedding","metadata":{"release_date":"2024-01-30","is_available_on_credits":true},"id":"parasail/parasail-bge-m3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-cydonia-24-v41","base_model_name":"parasail-cydonia-24-v41","max_context_window":131072,"input_cost":0.3,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-cydonia-24-v41","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":5.5717,"average_ttft":null,"average_latency":1.8793,"uptime_percent":100,"cache_hit_percentage":49.4382},"throughput":{"average_tps":5.5717,"average_ttft":null,"average_latency":1.8793,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-deepseek-v4-flash","base_model_name":"parasail-deepseek-v4-flash","max_context_window":1000000,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.07,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}}},"id":"parasail/parasail-deepseek-v4-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":46.8227,"average_ttft":null,"average_latency":1.5223,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":46.8227,"average_ttft":null,"average_latency":1.5223,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-deepseek-v4-flash-0731","base_model_name":"parasail/parasail-deepseek-v4-flash-0731","max_context_window":1048576,"input_cost":0.14,"output_cost":0.28,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-31","is_available_on_credits":true},"id":"parasail/parasail-deepseek-v4-flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-deepseek-v4-pro","base_model_name":"parasail-deepseek-v4-pro","max_context_window":1000000,"input_cost":1.74,"output_cost":3.48,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"parasail/parasail-deepseek-v4-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.0294,"average_ttft":null,"average_latency":3.4013,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.0294,"average_ttft":null,"average_latency":3.4013,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-deepseek-v4-pro-0813","base_model_name":"parasail/parasail-deepseek-v4-pro-0813","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-13","is_available_on_credits":true},"id":"parasail/parasail-deepseek-v4-pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-deepseek-v41-flash","base_model_name":"parasail/parasail-deepseek-v41-flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10","is_available_on_credits":true},"id":"parasail/parasail-deepseek-v41-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-gemma-4-26b-a4b-it","base_model_name":"parasail-gemma-4-26b-a4b-it","max_context_window":262144,"input_cost":0.13,"output_cost":0.4,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-gemma-4-26b-a4b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":18.1026,"average_ttft":2.0591,"average_latency":1.7123,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.1026,"average_ttft":2.0591,"average_latency":1.7123,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-gemma-4-31b-it","base_model_name":"parasail-gemma-4-31b-it","max_context_window":262144,"input_cost":0.15,"output_cost":0.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-gemma-4-31b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":3.7236,"average_ttft":null,"average_latency":1.7068,"uptime_percent":100,"cache_hit_percentage":9.6774},"throughput":{"average_tps":3.7236,"average_ttft":null,"average_latency":1.7068,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-gemma3-27b-it","base_model_name":"parasail-gemma3-27b-it","max_context_window":131072,"input_cost":0.08,"output_cost":0.45,"cache_hit_input_cost":0.008,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-gemma3-27b-it","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":19.6659,"average_ttft":null,"average_latency":5.9888,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.6659,"average_ttft":null,"average_latency":5.9888,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-glm-52","base_model_name":"parasail/parasail-glm-52","max_context_window":262144,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16","is_available_on_credits":true},"id":"parasail/parasail-glm-52","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-glm-53","base_model_name":"parasail/parasail-glm-53","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18","is_available_on_credits":true},"id":"parasail/parasail-glm-53","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-glm-53-flash","base_model_name":"parasail/parasail-glm-53-flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26","is_available_on_credits":true},"id":"parasail/parasail-glm-53-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-glm-53-flash-nvfp4","base_model_name":"parasail/parasail-glm-53-flash-nvfp4","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.tool_choice_support","capability.vision","cost_tiers","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-09-28","is_available_on_credits":true},"id":"parasail/parasail-glm-53-flash-nvfp4","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-gpt-oss-120b","base_model_name":"parasail/parasail-gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["parasail/parasail-gpt-oss-120b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05"},"id":"parasail/parasail-gpt-oss-120b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":94.0229,"average_ttft":null,"average_latency":0.468,"uptime_percent":100,"cache_hit_percentage":64},"throughput":{"average_tps":94.0229,"average_ttft":null,"average_latency":0.468,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-gpt-oss-120b-fast","base_model_name":"parasail/parasail-gpt-oss-120b-fast","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05","is_available_on_credits":true},"id":"parasail/parasail-gpt-oss-120b-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-gpt-oss-20b","base_model_name":"parasail-gpt-oss-20b","max_context_window":131072,"input_cost":0.04,"output_cost":0.2,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-gpt-oss-20b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":22.3845,"average_ttft":null,"average_latency":1.4742,"uptime_percent":100,"cache_hit_percentage":64},"throughput":{"average_tps":22.3845,"average_ttft":null,"average_latency":1.4742,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-gpt-oss-20b-fast-mem0","base_model_name":"parasail/parasail-gpt-oss-20b-fast-mem0","max_context_window":131072,"input_cost":0.04,"output_cost":0.15,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["parasail/parasail-gpt-oss-20b-fast-mem0"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-05"},"id":"parasail/parasail-gpt-oss-20b-fast-mem0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":126.6926,"average_ttft":null,"average_latency":7.0426,"uptime_percent":99.9952,"cache_hit_percentage":72.556},"throughput":{"average_tps":126.6926,"average_ttft":null,"average_latency":7.0426,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-kimi-k26","base_model_name":"parasail-kimi-k26","max_context_window":262144,"input_cost":0.75,"output_cost":3.5,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-kimi-k26","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":57.2182,"average_ttft":null,"average_latency":1.1185,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":57.2182,"average_ttft":null,"average_latency":1.1185,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-kimi-k3","base_model_name":"parasail/parasail-kimi-k3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16","is_available_on_credits":true},"id":"parasail/parasail-kimi-k3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-llama-32-3b-instruct","base_model_name":"parasail/parasail-llama-32-3b-instruct","max_context_window":131072,"input_cost":0.05,"output_cost":0.33,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-25","is_available_on_credits":true},"id":"parasail/parasail-llama-32-3b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-llama-33-70b-fp8","base_model_name":"parasail-llama-33-70b-fp8","max_context_window":131072,"input_cost":0.22,"output_cost":0.5,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-18"},"id":"parasail/parasail-llama-33-70b-fp8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":20.1113,"average_ttft":null,"average_latency":0.7409,"uptime_percent":100,"cache_hit_percentage":22.2222},"throughput":{"average_tps":20.1113,"average_ttft":null,"average_latency":0.7409,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-llama-4-maverick-instruct-fp8","base_model_name":"parasail-llama-4-maverick-instruct-fp8","max_context_window":1048576,"input_cost":0.35,"output_cost":1,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-05"},"id":"parasail/parasail-llama-4-maverick-instruct-fp8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":20.6784,"average_ttft":null,"average_latency":0.7709,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":20.6784,"average_ttft":null,"average_latency":0.7709,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-minimax-m3","base_model_name":"parasail/parasail-minimax-m3","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-31","is_available_on_credits":true},"id":"parasail/parasail-minimax-m3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-mistral-small-32-24b","base_model_name":"parasail-mistral-small-32-24b","max_context_window":128000,"input_cost":0.09,"output_cost":0.6,"cache_hit_input_cost":0.009,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-mistral-small-32-24b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":15.489,"average_ttft":null,"average_latency":0.8645,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":15.489,"average_ttft":null,"average_latency":0.8645,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-mistralaimistral-nemo","base_model_name":"parasail/parasail-mistralaimistral-nemo","max_context_window":131072,"input_cost":0.03,"output_cost":0.03,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-07-18","is_available_on_credits":true},"id":"parasail/parasail-mistralaimistral-nemo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":6.0892,"average_ttft":null,"average_latency":0.4927,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.0892,"average_ttft":null,"average_latency":0.4927,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen-3-next-80b-instruct","base_model_name":"parasail-qwen-3-next-80b-instruct","max_context_window":262144,"input_cost":0.1,"output_cost":1.1,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen-3-next-80b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.9273,"average_ttft":null,"average_latency":0.3409,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.9273,"average_ttft":null,"average_latency":0.3409,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen25-vl-72b-instruct","base_model_name":"parasail-qwen25-vl-72b-instruct","max_context_window":131072,"input_cost":0.8,"output_cost":1,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-qwen25-vl-72b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.7738,"average_ttft":null,"average_latency":0.4593,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.7738,"average_ttft":null,"average_latency":0.4593,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3-235b-a22b-instruct-2507","base_model_name":"parasail-qwen3-235b-a22b-instruct-2507","max_context_window":262144,"input_cost":0.1,"output_cost":0.6,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3-235b-a22b-instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.7849,"average_ttft":null,"average_latency":0.6532,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.7849,"average_ttft":null,"average_latency":0.6532,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3-coder-next","base_model_name":"parasail-qwen3-coder-next","max_context_window":262144,"input_cost":0.15,"output_cost":0.8,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3-coder-next","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.4719,"average_ttft":null,"average_latency":0.4533,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.4719,"average_ttft":null,"average_latency":0.4533,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3-vl-235b-a22b-instruct","base_model_name":"parasail-qwen3-vl-235b-a22b-instruct","max_context_window":131072,"input_cost":0.21,"output_cost":1.9,"cache_hit_input_cost":0.021,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3-vl-235b-a22b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.1805,"average_ttft":null,"average_latency":0.879,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.1805,"average_ttft":null,"average_latency":0.879,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen35-397b-a17b","base_model_name":"parasail-qwen35-397b-a17b","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen35-397b-a17b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.7813,"average_ttft":null,"average_latency":1.496,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.7813,"average_ttft":null,"average_latency":1.496,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-qwen35-9b","base_model_name":"parasail/parasail-qwen35-9b","max_context_window":262144,"input_cost":0.1,"output_cost":0.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-10","is_available_on_credits":true},"id":"parasail/parasail-qwen35-9b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/parasail-qwen38-27b","base_model_name":"parasail/parasail-qwen38-27b","max_context_window":262144,"input_cost":0.24,"output_cost":2.2,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-14","is_available_on_credits":true},"id":"parasail/parasail-qwen38-27b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3p5-35b-a3b","base_model_name":"parasail-qwen3p5-35b-a3b","max_context_window":262144,"input_cost":0.25,"output_cost":1,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3p5-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":116.4159,"average_ttft":null,"average_latency":0.5498,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":116.4159,"average_ttft":null,"average_latency":0.5498,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3p6-35b-a3b","base_model_name":"parasail-qwen3p6-35b-a3b","max_context_window":262144,"input_cost":0.15,"output_cost":1,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3p6-35b-a3b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":70.2576,"average_ttft":null,"average_latency":0.9109,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":70.2576,"average_ttft":null,"average_latency":0.9109,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-qwen3vl-8b-instruct","base_model_name":"parasail-qwen3vl-8b-instruct","max_context_window":262144,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/parasail-qwen3vl-8b-instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":36.3376,"average_ttft":null,"average_latency":0.696,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":36.3376,"average_ttft":null,"average_latency":0.696,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-skyfall-36b-v2-fp8","base_model_name":"parasail-skyfall-36b-v2-fp8","max_context_window":32768,"input_cost":0.55,"output_cost":0.8,"cache_hit_input_cost":0.055,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-skyfall-36b-v2-fp8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.8103,"average_ttft":null,"average_latency":0.6837,"uptime_percent":100,"cache_hit_percentage":98.8764},"throughput":{"average_tps":31.8103,"average_ttft":null,"average_latency":0.6837,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/parasail-ui-tars-1p5-7b","base_model_name":"parasail-ui-tars-1p5-7b","max_context_window":128000,"input_cost":0.1,"output_cost":0.2,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"parasail/parasail-ui-tars-1p5-7b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":29.5577,"average_ttft":null,"average_latency":0.3441,"uptime_percent":100,"cache_hit_percentage":40},"throughput":{"average_tps":29.5577,"average_ttft":null,"average_latency":0.3441,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen2.5-VL-72B-Instruct","base_model_name":"Qwen/Qwen2.5-VL-72B-Instruct","max_context_window":131072,"input_cost":0.8,"output_cost":1,"cache_hit_input_cost":0.08,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-09-19"},"id":"parasail/Qwen/Qwen2.5-VL-72B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":24.5222,"average_ttft":null,"average_latency":0.4078,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.5222,"average_ttft":null,"average_latency":0.4078,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3-235B-A22B-Instruct-2507","base_model_name":"Qwen/Qwen3-235B-A22B-Instruct-2507","max_context_window":262144,"input_cost":0.1,"output_cost":0.6,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["Qwen/Qwen3-235B-A22B-Instruct-2507"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3-235B-A22B-Instruct-2507","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":25.5646,"average_ttft":null,"average_latency":0.926,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":25.5646,"average_ttft":null,"average_latency":0.926,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3-Coder-Next","base_model_name":"Qwen/Qwen3-Coder-Next","max_context_window":262144,"input_cost":0.15,"output_cost":0.8,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3-Coder-Next","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.2727,"average_ttft":null,"average_latency":0.6567,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.2727,"average_ttft":null,"average_latency":0.6567,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3-Next-80B-A3B-Instruct","base_model_name":"Qwen/Qwen3-Next-80B-A3B-Instruct","max_context_window":262144,"input_cost":0.1,"output_cost":1.1,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3-Next-80B-A3B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":19.4495,"average_ttft":null,"average_latency":0.636,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":19.4495,"average_ttft":null,"average_latency":0.636,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3-VL-235B-A22B-Instruct","base_model_name":"Qwen/Qwen3-VL-235B-A22B-Instruct","max_context_window":131072,"input_cost":0.21,"output_cost":1.9,"cache_hit_input_cost":0.021,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3-VL-235B-A22B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":32.3589,"average_ttft":null,"average_latency":1.0507,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":32.3589,"average_ttft":null,"average_latency":1.0507,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3-VL-8B-Instruct","base_model_name":"Qwen/Qwen3-VL-8B-Instruct","max_context_window":262144,"input_cost":0.25,"output_cost":0.75,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3-VL-8B-Instruct","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":9.9039,"average_ttft":null,"average_latency":3.5426,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.9039,"average_ttft":null,"average_latency":3.5426,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3.5-35B-A3B","base_model_name":"Qwen/Qwen3.5-35B-A3B","max_context_window":262144,"input_cost":0.25,"output_cost":1,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3.5-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":83.5796,"average_ttft":null,"average_latency":0.7657,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":83.5796,"average_ttft":null,"average_latency":0.7657,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3.5-35B-A3B-FP8","base_model_name":"Qwen/Qwen3.5-35B-A3B-FP8","max_context_window":262144,"input_cost":0.25,"output_cost":1,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3.5-35B-A3B-FP8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":78.7148,"average_ttft":null,"average_latency":0.8936,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":78.7148,"average_ttft":null,"average_latency":0.8936,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3.5-397B-A17B","base_model_name":"Qwen/Qwen3.5-397B-A17B","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3.5-397B-A17B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":42.7842,"average_ttft":null,"average_latency":1.4974,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":42.7842,"average_ttft":null,"average_latency":1.4974,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/qwen/qwen3.5-9b","base_model_name":"parasail/qwen/qwen3.5-9b","max_context_window":262144,"input_cost":0.1,"output_cost":0.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-10","is_available_on_credits":true},"id":"parasail/qwen/qwen3.5-9b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/Qwen/Qwen3.5-9B","base_model_name":"parasail/Qwen/Qwen3.5-9B","max_context_window":262144,"input_cost":0.1,"output_cost":0.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-10","is_available_on_credits":true},"id":"parasail/Qwen/Qwen3.5-9B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/Qwen/Qwen3.6-35B-A3B","base_model_name":"Qwen/Qwen3.6-35B-A3B","max_context_window":262144,"input_cost":0.15,"output_cost":1,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"parasail/Qwen/Qwen3.6-35B-A3B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":60.4844,"average_ttft":null,"average_latency":1.1671,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":60.4844,"average_ttft":null,"average_latency":1.1671,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/Qwen/Qwen3.8-27B","base_model_name":"parasail/Qwen/Qwen3.8-27B","max_context_window":262144,"input_cost":0.24,"output_cost":2.2,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-14","is_available_on_credits":true},"id":"parasail/Qwen/Qwen3.8-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/TheDrummer/Cydonia-24B-v4.1","base_model_name":"TheDrummer/Cydonia-24B-v4.1","max_context_window":131072,"input_cost":0.3,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-27"},"id":"parasail/TheDrummer/Cydonia-24B-v4.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":3.0478,"average_ttft":null,"average_latency":3.2811,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":3.0478,"average_ttft":null,"average_latency":3.2811,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/TheDrummer/Skyfall-36B-v2","base_model_name":"TheDrummer/Skyfall-36B-v2","max_context_window":32768,"input_cost":0.55,"output_cost":0.8,"cache_hit_input_cost":0.055,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-10"},"id":"parasail/TheDrummer/Skyfall-36B-v2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":20.6881,"average_ttft":null,"average_latency":0.4834,"uptime_percent":100,"cache_hit_percentage":83.8095},"throughput":{"average_tps":20.6881,"average_ttft":null,"average_latency":0.4834,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/z-ai/glm-5.3","base_model_name":"parasail/z-ai/glm-5.3","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18","is_available_on_credits":true},"id":"parasail/z-ai/glm-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"parasail/zai-org/GLM-5.2","base_model_name":"zai-org/GLM-5.2","max_context_window":262144,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"parasail/zai-org/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":65.8063,"average_ttft":null,"average_latency":0.9746,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":65.8063,"average_ttft":null,"average_latency":0.9746,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/zai-org/GLM-5.2-FP8","base_model_name":"parasail/zai-org/GLM-5.2-FP8","max_context_window":262144,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-16","is_available_on_credits":true},"id":"parasail/zai-org/GLM-5.2-FP8","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/zai-org/GLM-5.3","base_model_name":"parasail/zai-org/GLM-5.3","max_context_window":1048576,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18","is_available_on_credits":true},"id":"parasail/zai-org/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Parasail","provider_id":"parasail","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.055705Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.parasail.io/v1/models"},"kind":"host","id":"parasail"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"parasail/zai-org/GLM-5.3-Flash","base_model_name":"parasail/zai-org/GLM-5.3-Flash","max_context_window":1048576,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26","is_available_on_credits":true},"id":"parasail/zai-org/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-fable-5","base_model_name":"","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}}},"id":"perplexity/anthropic/claude-fable-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-fable-5-1","base_model_name":"","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0.25,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-fable-5-1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-haiku-4-5","base_model_name":"","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-haiku-4-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-4-5","base_model_name":"","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-opus-4-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-4-6","base_model_name":"","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-opus-4-6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-4-7","base_model_name":"","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-opus-4-7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-4-8","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}}},"id":"perplexity/anthropic/claude-opus-4-8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-5","base_model_name":"","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7752095907502038,"ci_lo":0.6977633822227692,"model":"claude-opus-5","config":"mini_swe_agent_claude_opus_5_max","n_runs":4,"source":"deep-swe","ci_half":0.03872310426371729,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7364864864864865,"pass_at_4":0.8849557522123894,"pass_rate":0.7364864864864865,"n_attempted":444,"ci_attempted":444,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":11.837583271396396,"n_tasks_in_set":113,"median_cost_usd":10.4281505,"mean_agent_steps":99.0427927927928,"reasoning_effort":"max","mean_cache_tokens":14784785.963963963,"mean_input_tokens":15025834.39864865,"n_tasks_attempted":113,"mean_output_tokens":117565.6936936937,"median_agent_steps":90.5,"n_tasks_passed_any":100,"median_input_tokens":12130307.5,"median_output_tokens":113366.5,"mean_duration_seconds":1911.819866231982,"median_duration_seconds":1801.1237265,"median_peak_context_tokens":215810,"median_output_tokens_to_pass":112874}}},"id":"perplexity/anthropic/claude-opus-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-opus-5-5","base_model_name":"","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-opus-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-sonnet-4-5","base_model_name":"","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-sonnet-4-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-sonnet-4-6","base_model_name":"","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}}},"id":"perplexity/anthropic/claude-sonnet-4-6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-sonnet-5","base_model_name":"","max_context_window":200000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}}},"id":"perplexity/anthropic/claude-sonnet-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/anthropic/claude-sonnet-5-5","base_model_name":"","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/anthropic/claude-sonnet-5-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/deepseek-v4-pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.044,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"perplexity/deepseek-v4-pro-0813","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/glm-5.3","base_model_name":"","max_context_window":1000000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}}},"id":"perplexity/glm-5.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/glm-5.3-flash","base_model_name":"","max_context_window":1000000,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}}},"id":"perplexity/glm-5.3-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3-flash-preview","base_model_name":"","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/google/gemini-3-flash-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.1-flash-lite","base_model_name":"","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/google/gemini-3.1-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.1-pro-preview","base_model_name":"","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}}},"id":"perplexity/google/gemini-3.1-pro-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.5-flash","base_model_name":"","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}}},"id":"perplexity/google/gemini-3.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.5-flash-lite","base_model_name":"","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/google/gemini-3.5-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.6-flash","base_model_name":"","max_context_window":1048576,"input_cost":1.5,"output_cost":7.5,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5038626982845081,"ci_lo":0.4297656202995626,"model":"gemini-3-6-flash","config":"mini_swe_agent_gemini_3_6_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.037048538992472776,"harness":"mini-swe-agent","version":"v1.1","n_passed":211,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":211,"pass_at_1":0.4668141592920354,"pass_at_4":0.7522123893805309,"pass_rate":0.4668141592920354,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.419013277333334,"n_tasks_in_set":113,"median_cost_usd":3.444695325000001,"mean_agent_steps":116.73333333333333,"reasoning_effort":"high","mean_cache_tokens":11254636.448888889,"mean_input_tokens":12595957.344444444,"n_tasks_attempted":113,"mean_output_tokens":95844.86222222222,"median_agent_steps":108,"n_tasks_passed_any":85,"median_input_tokens":8949018.5,"median_output_tokens":86727,"mean_duration_seconds":1477.8607510707964,"median_duration_seconds":1214.8670550000002,"median_peak_context_tokens":151398.5,"median_output_tokens_to_pass":83414}}},"id":"perplexity/google/gemini-3.6-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.7-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}}},"id":"perplexity/google/gemini-3.7-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/google/gemini-3.8-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7524281656234058,"ci_lo":0.7240819014906883,"model":"gemini-3-8-flash","config":"mini_swe_agent_gemini_3_8_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.014173132066358783,"harness":"mini-swe-agent","version":"v1.1","n_passed":330,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":330,"pass_at_1":0.738255033557047,"pass_at_4":0.8584070796460177,"pass_rate":0.738255033557047,"n_attempted":447,"ci_attempted":447,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.362349413758389,"n_tasks_in_set":113,"median_cost_usd":2.1098912999999997,"mean_agent_steps":166.3131991051454,"reasoning_effort":"high","mean_cache_tokens":21456039.230425056,"mean_input_tokens":21734449.25279642,"n_tasks_attempted":113,"mean_output_tokens":143242.6644295302,"median_agent_steps":161,"n_tasks_passed_any":97,"median_input_tokens":18026661,"median_output_tokens":138377,"mean_duration_seconds":686.7691519843399,"median_duration_seconds":604.643838,"median_peak_context_tokens":215558,"median_output_tokens_to_pass":136617.5}}},"id":"perplexity/google/gemini-3.8-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/kimi-k3","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}}},"id":"perplexity/kimi-k3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":{"cost":4.654682129933482,"intelligence":0.6851441241685144,"latency":4541.447376412417,"speed":17.94578596140072,"context":130945,"passAt4":0.8938053097345132}},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/nemotron-3-ultra-550b-a55b","base_model_name":"","max_context_window":262144,"input_cost":0.25,"output_cost":2.5,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/nemotron-3-ultra-550b-a55b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5","base_model_name":"","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5-mini","base_model_name":"","max_context_window":400000,"input_cost":0.25,"output_cost":2,"cache_hit_input_cost":0.025,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5-nano","base_model_name":"","max_context_window":400000,"input_cost":0.05,"output_cost":0.4,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5-nano","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.1","base_model_name":"","max_context_window":400000,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":0.125,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.2","base_model_name":"","max_context_window":400000,"input_cost":1.75,"output_cost":14,"cache_hit_input_cost":0.175,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.3-codex","base_model_name":"","max_context_window":400000,"input_cost":3.5,"output_cost":28,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5.3-codex","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.4","base_model_name":"","max_context_window":1050000,"input_cost":2.5,"output_cost":15,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5327201646116306,"ci_lo":0.502678065476865,"model":"gpt-5-4","config":"mini_swe_agent_gpt_5_4_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.015021049567382833,"harness":"mini-swe-agent","version":"v1.1","n_passed":234,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":234,"pass_at_1":0.5176991150442478,"pass_at_4":0.7787610619469026,"pass_rate":0.5176991150442478,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.6524577245575225,"n_tasks_in_set":113,"median_cost_usd":4.3528565,"mean_agent_steps":70.47123893805309,"reasoning_effort":"xhigh","mean_cache_tokens":8613618.407079646,"mean_input_tokens":9418920.763274336,"n_tasks_attempted":113,"mean_output_tokens":71408.87389380531,"median_agent_steps":63,"n_tasks_passed_any":88,"median_input_tokens":6869950.5,"median_output_tokens":67233.5,"mean_duration_seconds":1368.707164818584,"median_duration_seconds":1209.517342,"median_peak_context_tokens":172734.5,"median_output_tokens_to_pass":64347}}},"id":"perplexity/openai/gpt-5.4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.4-mini","base_model_name":"","max_context_window":400000,"input_cost":0.75,"output_cost":4.5,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5.4-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.4-nano","base_model_name":"","max_context_window":400000,"input_cost":0.2,"output_cost":1.25,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-5.4-nano","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.5","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}}},"id":"perplexity/openai/gpt-5.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.6-luna","base_model_name":"","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0.25,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}}},"id":"perplexity/openai/gpt-5.6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.6-sol","base_model_name":"","max_context_window":1050000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.4,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}}},"id":"perplexity/openai/gpt-5.6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-5.6-terra","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}}},"id":"perplexity/openai/gpt-5.6-terra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-6-astra","base_model_name":"","max_context_window":1050000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7698044042186275,"ci_lo":0.7124964807371247,"model":"gpt-6-astra","config":"mini_swe_agent_gpt_6_astra_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.02865396174075141,"harness":"mini-swe-agent","version":"v1.1","n_passed":335,"provider":"openai","ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":335,"pass_at_1":0.7411504424778761,"pass_at_4":0.8053097345132744,"pass_rate":0.7411504424778761,"cost_basis":"Current pricing at all context lengths: $10/M uncached input, $12.50/M cache writes, $1/M cache reads, $50/M output; no separate compute-unit fee.","n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.429117203539823,"n_tasks_in_set":113,"median_cost_usd":3.8406789999999997,"mean_agent_steps":28.754424778761063,"reasoning_effort":"xhigh","mean_cache_tokens":1326921.6836283186,"mean_input_tokens":1456927.0929203539,"n_tasks_attempted":113,"mean_compute_units":752203.0973451327,"mean_output_tokens":29557.327433628318,"median_agent_steps":26,"n_tasks_passed_any":91,"median_input_tokens":1163918.5,"completed_by_attempt":[113,113,113,113],"median_compute_units":662371.5,"median_output_tokens":28542.5,"pass_rate_by_attempt":[0.7079646017699115,0.7345132743362832,0.7787610619469026,0.7433628318584071],"mean_duration_seconds":1132.4004424778761,"mean_reasoning_tokens":11255.66592920354,"mean_cache_read_tokens":1326921.6836283186,"mean_cache_write_tokens":129710.02212389381,"median_duration_seconds":959,"median_reasoning_tokens":10434,"median_cache_read_tokens":1035975,"median_cache_write_tokens":103995,"mean_uncached_input_tokens":295.3871681415929,"median_peak_context_tokens":null,"median_output_tokens_to_pass":28361,"median_uncached_input_tokens":87}}},"id":"perplexity/openai/gpt-6-astra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-6-luna","base_model_name":"","max_context_window":1050000,"input_cost":0.1,"output_cost":0.5,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0.125,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-6-sol","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/openai/gpt-6.1-sol","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.1,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/openai/gpt-6.1-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":2,"min":0},"default":0.2,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.9,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":0},"default":1,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":0},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/sonar","base_model_name":"perplexity/sonar","max_context_window":127000,"input_cost":0.25,"output_cost":2.5,"cache_hit_input_cost":0.0625,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["perplexity/sonar"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":127000,"release_date":"2025-01-21","prompt_training":false,"stream_cancellation_supported":true},"id":"perplexity/sonar","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.5172,"average_ttft":1.3164,"average_latency":2.17,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.5172,"average_ttft":1.3164,"average_latency":2.17,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.20-multi-agent","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/xai/grok-4.20-multi-agent","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.20-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/xai/grok-4.20-non-reasoning","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.20-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/xai/grok-4.20-reasoning","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.3","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/xai/grok-4.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.5","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5604186651978057,"ci_lo":0.5148025737402474,"model":"grok-4-5","config":"mini_swe_agent_grok_4_5_high","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":243,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":243,"pass_at_1":0.5376106194690266,"pass_at_4":0.7787610619469026,"pass_rate":0.5376106194690266,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.4157481725663716,"n_tasks_in_set":113,"median_cost_usd":2.02311,"mean_agent_steps":61.33185840707964,"reasoning_effort":"high","mean_cache_tokens":3943846.5132743362,"mean_input_tokens":4059182.975663717,"n_tasks_attempted":113,"mean_output_tokens":35525.33185840708,"median_agent_steps":56,"n_tasks_passed_any":88,"median_input_tokens":3293744.5,"median_output_tokens":34250,"mean_duration_seconds":484.7029359800885,"median_duration_seconds":430.0852805,"median_peak_context_tokens":94044,"median_output_tokens_to_pass":33872}}},"id":"perplexity/xai/grok-4.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.6","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.697586806790726,"ci_lo":0.6519707153331677,"model":"grok-4-6","config":"mini_swe_agent_grok_4_6_medium","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":305,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":305,"pass_at_1":0.6747787610619469,"pass_at_4":0.8407079646017699,"pass_rate":0.6747787610619469,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4489837522123894,"n_tasks_in_set":113,"median_cost_usd":2.945834,"mean_agent_steps":70.28982300884955,"reasoning_effort":"medium","mean_cache_tokens":5533327.0088495575,"mean_input_tokens":5725195.139380531,"n_tasks_attempted":113,"mean_output_tokens":49763.99778761062,"median_agent_steps":66,"n_tasks_passed_any":95,"median_input_tokens":4705124,"median_output_tokens":48585.5,"mean_duration_seconds":895.5380579646018,"median_duration_seconds":860.0352045,"median_peak_context_tokens":116622,"median_output_tokens_to_pass":48346}}},"id":"perplexity/xai/grok-4.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Perplexity","provider_id":"perplexity","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.569957Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.perplexity.ai/v1/models"},"kind":"host","id":"perplexity"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"perplexity/xai/grok-4.7","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":2,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"perplexity/xai/grok-4.7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Prism","provider_id":"prism","extra_kwargs":{},"created_at":"2026-09-15T04:32:46.120068Z","updated_at":"2026-09-15T04:32:46.120073Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.prisminference.com/models"},"kind":"host","id":"prism"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"prism/deepseek-v4-flash","base_model_name":"deepseek-v4-flash","max_context_window":1000000,"input_cost":0.03,"output_cost":0.55,"cache_hit_input_cost":0.016,"cache_creation_input_cost":0,"respan_discount_rate":0.2,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"max_output_tokens":384000},"id":"prism/deepseek-v4-flash","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":88.3784,"average_ttft":0.6963,"average_latency":7.2928,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":88.3784,"average_ttft":0.6963,"average_latency":7.2928,"number_of_requests":null},"benchmark":{"cost":0.10023560370265487,"intelligence":0.5331858407079646,"latency":1438.9961937522125,"speed":74.83482068364452,"context":201636.5,"passAt4":0.8053097345132744}},{"project":null,"provider":{"project":null,"provider_name":"Prism","provider_id":"prism","extra_kwargs":{},"created_at":"2026-09-15T04:32:46.120068Z","updated_at":"2026-09-15T04:32:46.120073Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.prisminference.com/models"},"kind":"host","id":"prism"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"prism/deepseek-v4.1-flash","base_model_name":"deepseek-v4.1-flash","max_context_window":1000000,"input_cost":0.17,"output_cost":0.63,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":0.2,"overridden_fields":["input_cost","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"max_output_tokens":384000},"id":"prism/deepseek-v4.1-flash","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":244.0035,"average_ttft":0.459,"average_latency":3.0117,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":244.0035,"average_ttft":0.459,"average_latency":3.0117,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Prism","provider_id":"prism","extra_kwargs":{},"created_at":"2026-09-15T04:32:46.120068Z","updated_at":"2026-09-15T04:32:46.120073Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.prisminference.com/models"},"kind":"host","id":"prism"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"prism/gemma-4-31b","base_model_name":"","max_context_window":32768,"input_cost":0.14,"output_cost":0.4,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"prism/gemma-4-31b","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.6-flash","base_model_name":"qwen/qwen3.6-flash","max_context_window":1000000,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-04-16","pricing_basis":"DashScope International OpenAI-compatible endpoint stable list price","pricing_tiers":[{"input_tokens_up_to":256000,"input_cost_per_million":0.25,"output_cost_per_million":1.5,"implicit_cache_hit_cost_per_million":0.05},{"input_tokens_up_to":1000000,"input_cost_per_million":1,"output_cost_per_million":4,"implicit_cache_hit_cost_per_million":0.2}],"is_available_on_credits":false},"id":"qwen/qwen3.6-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.7-flash","base_model_name":"qwen/qwen3.7-flash","max_context_window":1000000,"input_cost":0.03,"output_cost":0.13,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-15","pricing_basis":"DashScope International OpenAI-compatible endpoint","pricing_tiers":[{"input_tokens_up_to":32000,"input_cost_per_million":0.03,"output_cost_per_million":0.13},{"input_tokens_up_to":256000,"input_cost_per_million":0.1,"output_cost_per_million":0.4},{"input_tokens_up_to":1000000,"input_cost_per_million":0.2,"output_cost_per_million":0.8}],"is_available_on_credits":true},"id":"qwen/qwen3.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":87.4648,"average_ttft":0.916,"average_latency":31.3254,"uptime_percent":100,"cache_hit_percentage":6.7088},"throughput":{"average_tps":87.4648,"average_ttft":0.916,"average_latency":31.3254,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.7-max","base_model_name":"qwen/qwen3.7-max","max_context_window":1000000,"input_cost":2.5,"output_cost":7.5,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1000000,"release_date":"2026-05-20","pricing_basis":"DashScope International OpenAI-compatible endpoint stable list price","pricing_tiers":[{"input_tokens_up_to":1000000,"input_cost_per_million":2.5,"output_cost_per_million":7.5,"implicit_cache_hit_cost_per_million":0.5}],"is_available_on_credits":false},"id":"qwen/qwen3.7-max","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.7-plus","base_model_name":"qwen/qwen3.7-plus","max_context_window":1000000,"input_cost":0.4,"output_cost":1.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-15","pricing_basis":"DashScope International OpenAI-compatible endpoint","pricing_tiers":[{"input_tokens_up_to":256000,"input_cost_per_million":0.4,"output_cost_per_million":1.6},{"input_tokens_up_to":1000000,"input_cost_per_million":1.2,"output_cost_per_million":4.8}],"is_available_on_credits":true},"id":"qwen/qwen3.7-plus","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":55.8843,"average_ttft":null,"average_latency":3.6683,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":55.8843,"average_ttft":null,"average_latency":3.6683,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.8-max","base_model_name":"qwen/qwen3.8-max","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"release_date":"2026-08-15","pricing_basis":"DashScope International OpenAI-compatible endpoint","pricing_tiers":[{"input_tokens_up_to":1000000,"input_cost_per_million":2,"output_cost_per_million":6,"implicit_cache_hit_cost_per_million":0.25}],"is_available_on_credits":true},"id":"qwen/qwen3.8-max","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":16.8199,"average_ttft":null,"average_latency":2.2592,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":16.8199,"average_ttft":null,"average_latency":2.2592,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Qwen","provider_id":"qwen","extra_kwargs":{},"created_at":"2026-08-14T01:33:18.054105Z","updated_at":"2026-08-14T01:33:18.054109Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"qwen"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"qwen/qwen3.8-max-0902","base_model_name":"qwen/qwen3.8-max-0902","max_context_window":1000000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","cost_tiers","display_name","function_call","image_support","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6012381717139396,"ci_lo":0.5479823182637887,"model":"qwen3-8-max","config":"mini_swe_agent_qwen3_8_max_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.026627926725075454,"harness":"mini-swe-agent","version":"v1.1","n_passed":258,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":258,"pass_at_1":0.5746102449888641,"pass_at_4":0.831858407079646,"pass_rate":0.5746102449888641,"n_attempted":449,"ci_attempted":449,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.7290646500445437,"n_tasks_in_set":113,"median_cost_usd":3.132689060000001,"mean_agent_steps":111.33853006681514,"reasoning_effort":"xhigh","mean_cache_tokens":12477251.240534522,"mean_input_tokens":12996066.461024499,"n_tasks_attempted":113,"mean_output_tokens":95075.18262806236,"median_agent_steps":102,"n_tasks_passed_any":94,"median_input_tokens":10163801,"median_output_tokens":89729,"mean_duration_seconds":2567.2746634654786,"median_duration_seconds":2424.198128,"median_peak_context_tokens":160572,"median_output_tokens_to_pass":91083}},"context_size":1000000,"release_date":"2026-09-02","pricing_basis":"QwenCloud and DashScope Singapore International OpenAI-compatible endpoint","pricing_tiers":[{"input_tokens_up_to":1000000,"input_cost_per_million":2,"output_cost_per_million":6,"implicit_cache_hit_cost_per_million":0.25}],"max_output_tokens":131072,"is_available_on_credits":true},"id":"qwen/qwen3.8-max-0902","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":12.1261,"average_ttft":null,"average_latency":2.3915,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":12.1261,"average_ttft":null,"average_latency":2.3915,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/deepseek-ai/DeepSeek-V4-Flash-0423","base_model_name":"","max_context_window":1048576,"input_cost":0.009,"output_cost":1.28,"cache_hit_input_cost":0.009,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24"},"id":"relace/deepseek-ai/DeepSeek-V4-Flash-0423","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"relace/deepseek-ai/DeepSeek-V4-Flash-0731","max_context_window":1048576,"input_cost":0.01,"output_cost":1.28,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-07-31"},"id":"relace/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":8.5258,"average_ttft":null,"average_latency":2.6755,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.5258,"average_ttft":null,"average_latency":2.6755,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"","max_context_window":1048576,"input_cost":0.4,"output_cost":3.5,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"relace/deepseek-ai/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"","max_context_window":1048576,"input_cost":0.134,"output_cost":3.5,"cache_hit_input_cost":0.134,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}}},"id":"relace/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.02,"output_cost":0.6,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-10"},"id":"relace/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/moonshotai/kimi-k3","base_model_name":"relace/moonshotai/kimi-k3","max_context_window":1048576,"input_cost":0.4,"output_cost":10,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","function_call","image_support","input_cost","max_context_window","output_cost"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-16"},"id":"relace/moonshotai/kimi-k3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":110.0535,"average_ttft":3.5288,"average_latency":4.8421,"uptime_percent":100,"cache_hit_percentage":33.5899},"throughput":{"average_tps":110.0535,"average_ttft":3.5288,"average_latency":4.8421,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/xiaomi/mimo-v2.6-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.04,"output_cost":1.28,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"relace/xiaomi/mimo-v2.6-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/z-ai/glm-5.2","base_model_name":"","max_context_window":1048576,"input_cost":0.18,"output_cost":4,"cache_hit_input_cost":0.18,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}}},"id":"relace/z-ai/glm-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/z-ai/glm-5.3","base_model_name":"","max_context_window":1048576,"input_cost":0.13,"output_cost":4,"cache_hit_input_cost":0.13,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18"},"id":"relace/z-ai/glm-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Relace","provider_id":"relace","extra_kwargs":{},"created_at":"2026-08-26T04:17:08.974137Z","updated_at":"2026-08-26T04:17:08.974154Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://models.relace.ai/models"},"kind":"host","id":"relace"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"relace/z-ai/glm-5.3-flash","base_model_name":"","max_context_window":1048576,"input_cost":0.035,"output_cost":0.5,"cache_hit_input_cost":0.035,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-28"},"id":"relace/z-ai/glm-5.3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Respan","provider_id":"respan","extra_kwargs":{},"created_at":"2026-09-24T09:54:18.518892Z","updated_at":"2026-09-24T09:54:18.518913Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"respan"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"span-01-free","base_model_name":"span-01-free","max_context_window":null,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"span-01-free","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":0.3163,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":0.3163,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Respan","provider_id":"respan","extra_kwargs":{},"created_at":"2026-09-24T09:54:18.518892Z","updated_at":"2026-09-24T09:54:18.518913Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"respan"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"span-01-pro","base_model_name":"span-01-pro","max_context_window":null,"input_cost":0.02,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["max_context_window"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":true},"id":"span-01-pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":0.6824,"uptime_percent":99.9835,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":0.6824,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Respan","provider_id":"respan","extra_kwargs":{},"created_at":"2026-09-24T09:54:18.518892Z","updated_at":"2026-09-24T09:54:18.518913Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"respan"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"span-router","base_model_name":"span-router","max_context_window":null,"input_cost":2,"output_cost":5,"cache_hit_input_cost":0.5,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["max_context_window","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"price_label":"Routed","is_available_on_credits":true},"id":"span-router","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":49.9741,"average_ttft":0.8928,"average_latency":1.6997,"uptime_percent":100,"cache_hit_percentage":6.3968},"throughput":{"average_tps":49.9741,"average_ttft":0.8928,"average_latency":1.6997,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/anthropic/claude-fable-5","base_model_name":"","max_context_window":200000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}},"release_date":"2026-07-07","is_available_on_credits":false},"id":"tera/anthropic/claude-fable-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/anthropic/claude-opus-4-8","base_model_name":"","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}},"release_date":"2026-07-07","is_available_on_credits":false},"id":"tera/anthropic/claude-opus-4-8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/anthropic/claude-sonnet-5","base_model_name":"","max_context_window":200000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"release_date":"2026-07-07","is_available_on_credits":false},"id":"tera/anthropic/claude-sonnet-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/deepseek-ai/DeepSeek-R1-0528","base_model_name":"","max_context_window":163840,"input_cost":1.35,"output_cost":5.4,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-08","is_available_on_credits":false},"id":"tera/deepseek-ai/DeepSeek-R1-0528","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/deepseek-ai/DeepSeek-V3.1","base_model_name":"","max_context_window":163840,"input_cost":0.6,"output_cost":1.7,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-28","is_available_on_credits":false},"id":"tera/deepseek-ai/DeepSeek-V3.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/deepseek-ai/DeepSeek-V3.2","base_model_name":"","max_context_window":163840,"input_cost":0.56,"output_cost":1.68,"cache_hit_input_cost":0.056,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-10","is_available_on_credits":false},"id":"tera/deepseek-ai/DeepSeek-V3.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/deepseek-ai/DeepSeek-V4-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.19,"output_cost":0.51,"cache_hit_input_cost":0.028,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-04-24","is_available_on_credits":false},"id":"tera/deepseek-ai/DeepSeek-V4-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/deepseek-ai/DeepSeek-V4-Pro","base_model_name":"","max_context_window":1048576,"input_cost":1.74,"output_cost":3.48,"cache_hit_input_cost":0.145,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24","is_available_on_credits":false},"id":"tera/deepseek-ai/DeepSeek-V4-Pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/google/gemma-4-26B-A4B-it","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-03","is_available_on_credits":false},"id":"tera/google/gemma-4-26B-A4B-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/meta-llama/Llama-3.3-70B-Instruct","base_model_name":"","max_context_window":128000,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29","is_available_on_credits":false},"id":"tera/meta-llama/Llama-3.3-70B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/MiniMaxAI/MiniMax-M2","base_model_name":"","max_context_window":196608,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-04","is_available_on_credits":false},"id":"tera/MiniMaxAI/MiniMax-M2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/moonshotai/kimi-k2-thinking","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-11-13","is_available_on_credits":false},"id":"tera/moonshotai/kimi-k2-thinking","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/moonshotai/Kimi-K2.5","base_model_name":"","max_context_window":262144,"input_cost":0.6,"output_cost":3,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-16","is_available_on_credits":false},"id":"tera/moonshotai/Kimi-K2.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/moonshotai/Kimi-K2.6","base_model_name":"","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.16,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-16","is_available_on_credits":false},"id":"tera/moonshotai/Kimi-K2.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/moonshotai/Kimi-K3","base_model_name":"","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-30","is_available_on_credits":false},"id":"tera/moonshotai/Kimi-K3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-5.5","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7350104457099735,"ci_lo":0.6056975188917963,"model":"gpt-5-5","config":"mini_swe_agent_gpt_5_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.06465646340908864,"harness":"mini-swe-agent","version":"v1.1","n_passed":303,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":303,"pass_at_1":0.6703539823008849,"pass_at_4":0.8849557522123894,"pass_rate":0.6703539823008849,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":7.226236674778761,"n_tasks_in_set":113,"median_cost_usd":6.110482499999999,"mean_agent_steps":82.01548672566372,"reasoning_effort":"xhigh","mean_cache_tokens":8032415.716814159,"mean_input_tokens":8372927.630530974,"n_tasks_attempted":113,"mean_output_tokens":46294.72345132743,"median_agent_steps":76.5,"n_tasks_passed_any":100,"median_input_tokens":6648149.5,"median_output_tokens":44492.5,"mean_duration_seconds":1806.3251869889382,"median_duration_seconds":1588.3887945,"median_peak_context_tokens":141957.5,"median_output_tokens_to_pass":44036}},"release_date":"2026-04-24","is_available_on_credits":false},"id":"tera/openai/gpt-5.5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-5.6-luna","base_model_name":"","max_context_window":1050000,"input_cost":0.2,"output_cost":1.2,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7117950123567105,"ci_lo":0.6319549876432895,"model":"gpt-5-6-luna","config":"mini_swe_agent_gpt_5_6_luna_max","n_runs":4,"source":"deep-swe","ci_half":0.03992001235671055,"harness":"mini-swe-agent","version":"v1.1","n_passed":301,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":301,"pass_at_1":0.671875,"pass_at_4":0.9026548672566371,"pass_rate":0.671875,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.028116810267857,"n_tasks_in_set":113,"median_cost_usd":2.2920917999999997,"mean_agent_steps":101.68080357142857,"reasoning_effort":"max","mean_cache_tokens":14666893.714285715,"mean_input_tokens":15443718.330357144,"n_tasks_attempted":113,"mean_output_tokens":73399.70758928571,"median_agent_steps":92.5,"n_tasks_passed_any":102,"median_input_tokens":12278493,"median_output_tokens":70253,"mean_duration_seconds":1122.9470243995536,"median_duration_seconds":982.9724034999999,"median_peak_context_tokens":201647,"median_output_tokens_to_pass":68234}},"release_date":"2026-07-09","is_available_on_credits":false},"id":"tera/openai/gpt-5.6-luna","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-5.6-sol","base_model_name":"","max_context_window":1050000,"input_cost":5,"output_cost":30,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7549648891650385,"ci_lo":0.6983684441682949,"model":"gpt-5-6-sol","config":"mini_swe_agent_gpt_5_6_sol_max","n_runs":4,"source":"deep-swe","ci_half":0.02829822249837175,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7266666666666667,"pass_at_4":0.8584070796460177,"pass_rate":0.7266666666666667,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":8.386436346666667,"n_tasks_in_set":113,"median_cost_usd":6.8414715,"mean_agent_steps":61.25333333333333,"reasoning_effort":"max","mean_cache_tokens":7419435.235555556,"mean_input_tokens":7907652.344444444,"n_tasks_attempted":113,"mean_output_tokens":60013.64444444444,"median_agent_steps":53,"n_tasks_passed_any":97,"median_input_tokens":5973865.5,"median_output_tokens":58786.5,"mean_duration_seconds":1128.624910331111,"median_duration_seconds":1013.6291865000001,"median_peak_context_tokens":177470.5,"median_output_tokens_to_pass":58467}},"release_date":"2026-07-09","is_available_on_credits":false},"id":"tera/openai/gpt-5.6-sol","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-5.6-terra","base_model_name":"","max_context_window":1050000,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7217999881740815,"ci_lo":0.6706612091651647,"model":"gpt-5-6-terra","config":"mini_swe_agent_gpt_5_6_terra_max","n_runs":4,"source":"deep-swe","ci_half":0.025569389504458404,"harness":"mini-swe-agent","version":"v1.1","n_passed":314,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":314,"pass_at_1":0.6962305986696231,"pass_at_4":0.8849557522123894,"pass_rate":0.6962305986696231,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.945847263858093,"n_tasks_in_set":113,"median_cost_usd":4.114557,"mean_agent_steps":75.9290465631929,"reasoning_effort":"max","mean_cache_tokens":8652201.720620843,"mean_input_tokens":9230560.541019956,"n_tasks_attempted":113,"mean_output_tokens":71938.62527716186,"median_agent_steps":71,"n_tasks_passed_any":100,"median_input_tokens":7288778,"median_output_tokens":70835,"mean_duration_seconds":1016.6698429312638,"median_duration_seconds":927.549964,"median_peak_context_tokens":177398,"median_output_tokens_to_pass":70061.5}},"release_date":"2026-07-09","is_available_on_credits":false},"id":"tera/openai/gpt-5.6-terra","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-oss-120b","base_model_name":"","max_context_window":131072,"input_cost":0.09,"output_cost":0.36,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13","is_available_on_credits":false},"id":"tera/openai/gpt-oss-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.07,"output_cost":0.25,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-08-13","is_available_on_credits":false},"id":"tera/openai/gpt-oss-20b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.4092,"average_ttft":null,"average_latency":1.6985,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":24.4092,"average_ttft":null,"average_latency":1.6985,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/Qwen/Qwen3-235B-A22B-Instruct-2507","base_model_name":"","max_context_window":262144,"input_cost":0.22,"output_cost":0.88,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13","is_available_on_credits":false},"id":"tera/Qwen/Qwen3-235B-A22B-Instruct-2507","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/Qwen/Qwen3-Coder-480B-A35B-Instruct","base_model_name":"","max_context_window":262144,"input_cost":0.22,"output_cost":1.8,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-13","is_available_on_credits":false},"id":"tera/Qwen/Qwen3-Coder-480B-A35B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/Qwen/Qwen3-Next-80B-A3B-Instruct","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-15","is_available_on_credits":false},"id":"tera/Qwen/Qwen3-Next-80B-A3B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/Qwen/Qwen3-Next-80B-A3B-Thinking","base_model_name":"","max_context_window":262144,"input_cost":0.15,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-15","is_available_on_credits":false},"id":"tera/Qwen/Qwen3-Next-80B-A3B-Thinking","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/zai-org/GLM-4.7","base_model_name":"","max_context_window":200000,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-01-06","is_available_on_credits":false},"id":"tera/zai-org/GLM-4.7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/zai-org/GLM-5","base_model_name":"","max_context_window":200000,"input_cost":1,"output_cost":3.2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-11","is_available_on_credits":false},"id":"tera/zai-org/GLM-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Tera","provider_id":"tera","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:55.233102Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://api.tera.gw/v1/models"},"kind":"host","id":"tera"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"tera/zai-org/GLM-5.2","base_model_name":"","max_context_window":262144,"input_cost":1.49,"output_cost":4.62,"cache_hit_input_cost":0.27,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-26","is_available_on_credits":false},"id":"tera/zai-org/GLM-5.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/arcee-ai/trinity-mini","base_model_name":"together_ai/arcee-ai/trinity-mini","max_context_window":128000,"input_cost":0.045000000000000005,"output_cost":0.15,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-15","is_available_on_credits":false},"id":"together_ai/arcee-ai/trinity-mini","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/arize-ai/qwen-2-1.5b-instruct","base_model_name":"together_ai/arize-ai/qwen-2-1.5b-instruct","max_context_window":32768,"input_cost":0.1,"output_cost":0.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-24","is_available_on_credits":false},"id":"together_ai/arize-ai/qwen-2-1.5b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/deepseek-coder-33b-instruct","base_model_name":"together_ai/deepseek-ai/deepseek-coder-33b-instruct","max_context_window":16384,"input_cost":0.8,"output_cost":0.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-02-07","is_available_on_credits":false},"id":"together_ai/deepseek-ai/deepseek-coder-33b-instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/deepseek-ai/DeepSeek-R1-0528","base_model_name":"deepseek-ai/DeepSeek-R1-0528","max_context_window":163840,"input_cost":3,"output_cost":7,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["deepseek-ai/DeepSeek-R1-0528"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-14"},"id":"together_ai/deepseek-ai/DeepSeek-R1-0528","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","base_model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","max_context_window":131072,"input_cost":2,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-28","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","base_model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","max_context_window":131072,"input_cost":0.18000000000000002,"output_cost":0.18000000000000002,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-29","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","base_model_name":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","max_context_window":131072,"input_cost":1.6,"output_cost":1.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-29","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-V3.1","base_model_name":"together_ai/deepseek-ai/DeepSeek-V3.1","max_context_window":131072,"input_cost":0.6,"output_cost":1.7,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-25","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-V3.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","base_model_name":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","max_context_window":1048576,"input_cost":0.13999999999999999,"output_cost":0.27999999999999997,"cache_hit_input_cost":0.030000000000000002,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5688553428582889,"ci_lo":0.4975163385576403,"model":"deepseek-v4-flash","config":"mini_swe_agent_deepseek_v4_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.035669502150324287,"harness":"mini-swe-agent","version":"v1.1","n_passed":241,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":241,"pass_at_1":0.5331858407079646,"pass_at_4":0.8053097345132744,"pass_rate":0.5331858407079646,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.10023560370265487,"n_tasks_in_set":113,"median_cost_usd":0.09124898719999996,"mean_agent_steps":152.87610619469027,"reasoning_effort":"max","mean_cache_tokens":19719518.867256638,"mean_input_tokens":19829931.451327432,"n_tasks_attempted":113,"mean_output_tokens":107687.02212389381,"median_agent_steps":148,"n_tasks_passed_any":91,"median_input_tokens":17312559.5,"median_output_tokens":104491.5,"mean_duration_seconds":1438.9961937522125,"median_duration_seconds":1383.7182735000001,"median_peak_context_tokens":201636.5,"median_output_tokens_to_pass":100483}},"release_date":"2026-08-28","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-V4-Flash-0731","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","base_model_name":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","max_context_window":1048576,"input_cost":1.32,"output_cost":3.96,"cache_hit_input_cost":0.12999999999999998,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-08-15","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-V4-Pro-0813","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","base_model_name":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","max_context_window":1048576,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.006,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-12","is_available_on_credits":false},"id":"together_ai/deepseek-ai/DeepSeek-V4.1-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/google/gemma-2-27b-it","base_model_name":"together_ai/google/gemma-2-27b-it","max_context_window":8192,"input_cost":0.8,"output_cost":0.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-02-23","is_available_on_credits":false},"id":"together_ai/google/gemma-2-27b-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/google/gemma-4-31B-it","base_model_name":"google/gemma-4-31B-it","max_context_window":262144,"input_cost":0.39,"output_cost":0.9700000000000001,"cache_hit_input_cost":0.02,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-02"},"id":"together_ai/google/gemma-4-31B-it","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":6.5693,"average_ttft":null,"average_latency":2.4356,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":6.5693,"average_ttft":null,"average_latency":2.4356,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Llama-3-8b-chat-hf","base_model_name":"together_ai/meta-llama/Llama-3-8b-chat-hf","max_context_window":8192,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["together_ai/meta-llama/Llama-3-8b-chat-hf"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":8000,"release_date":"2024-04-18","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"together_ai/meta-llama/Llama-3-8b-chat-hf","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Llama-3.1-405B-Instruct","base_model_name":"together_ai/meta-llama/Llama-3.1-405B-Instruct","max_context_window":4096,"input_cost":3.5,"output_cost":3.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06","is_available_on_credits":false},"id":"together_ai/meta-llama/Llama-3.1-405B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Llama-3.2-1B-Instruct","base_model_name":"together_ai/meta-llama/Llama-3.2-1B-Instruct","max_context_window":131072,"input_cost":0.060000000000000005,"output_cost":0.060000000000000005,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06","is_available_on_credits":false},"id":"together_ai/meta-llama/Llama-3.2-1B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Llama-3.2-3B-Instruct","base_model_name":"together_ai/meta-llama/Llama-3.2-3B-Instruct","max_context_window":131072,"input_cost":0.060000000000000005,"output_cost":0.060000000000000005,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06","is_available_on_credits":false},"id":"together_ai/meta-llama/Llama-3.2-3B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo","base_model_name":"meta-llama/Llama-3.3-70B-Instruct-Turbo","max_context_window":131072,"input_cost":1.0399999999999998,"output_cost":1.0399999999999998,"cache_hit_input_cost":0.088,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06"},"id":"together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.46,"average_ttft":null,"average_latency":0.8918,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.46,"average_ttft":null,"average_latency":0.8918,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","base_model_name":"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","max_context_window":1048576,"input_cost":0.18000000000000002,"output_cost":0.5900000000000001,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-05","is_available_on_credits":false},"id":"together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo","base_model_name":"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo","max_context_window":8192,"input_cost":0.88,"output_cost":0.88,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-18","is_available_on_credits":false},"id":"together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Meta-Llama-3-8B-Instruct","base_model_name":"together_ai/meta-llama/Meta-Llama-3-8B-Instruct","max_context_window":8192,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-18","is_available_on_credits":false},"id":"together_ai/meta-llama/Meta-Llama-3-8B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","base_model_name":"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","max_context_window":131072,"input_cost":0.88,"output_cost":0.88,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2024-07-21","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Meta-Llama-3.1-8B","base_model_name":"together_ai/meta-llama/Meta-Llama-3.1-8B","max_context_window":16384,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-04-18","is_available_on_credits":false},"id":"together_ai/meta-llama/Meta-Llama-3.1-8B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","base_model_name":"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","max_context_window":131072,"input_cost":0.18,"output_cost":0.18,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":131072,"release_date":"2025-03-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"together_ai/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/meta-models/Muse-Glimmer-30B","base_model_name":"together_ai/meta-models/Muse-Glimmer-30B","max_context_window":131072,"input_cost":0.35,"output_cost":1.5,"cache_hit_input_cost":0.04,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/meta-models/Muse-Glimmer-30B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/MiniMaxAI/MiniMax-M2.7","base_model_name":"MiniMaxAI/MiniMax-M2.7","max_context_window":196608,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-05"},"id":"together_ai/MiniMaxAI/MiniMax-M2.7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/MiniMaxAI/MiniMax-M3","base_model_name":"together_ai/MiniMaxAI/MiniMax-M3","max_context_window":524288,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.060000000000000005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27","is_available_on_credits":false},"id":"together_ai/MiniMaxAI/MiniMax-M3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/mistralai/Ministral-3-14B-Instruct-2512","base_model_name":"together_ai/mistralai/Ministral-3-14B-Instruct-2512","max_context_window":262144,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-02","is_available_on_credits":false},"id":"together_ai/mistralai/Ministral-3-14B-Instruct-2512","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/mistralai/Mistral-7B-Instruct-v0.1","base_model_name":"together_ai/mistralai/Mistral-7B-Instruct-v0.1","max_context_window":32768,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-09-28","is_available_on_credits":false},"id":"together_ai/mistralai/Mistral-7B-Instruct-v0.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/mistralai/Mistral-7B-Instruct-v0.3","base_model_name":"together_ai/mistralai/Mistral-7B-Instruct-v0.3","max_context_window":32768,"input_cost":0.2,"output_cost":0.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-05-22","is_available_on_credits":false},"id":"together_ai/mistralai/Mistral-7B-Instruct-v0.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/mistralai/Mistral-Small-24B-Instruct-2501","base_model_name":"together_ai/mistralai/Mistral-Small-24B-Instruct-2501","max_context_window":32768,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-30","is_available_on_credits":false},"id":"together_ai/mistralai/Mistral-Small-24B-Instruct-2501","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1","base_model_name":"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1","max_context_window":32768,"input_cost":0.6,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2023-12-12","is_available_on_credits":false},"id":"together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/moonshotai/Kimi-K2.5-fp4","base_model_name":"moonshotai/Kimi-K2.5-fp4","max_context_window":262144,"input_cost":0.5,"output_cost":2.8,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"together_ai/moonshotai/Kimi-K2.5-fp4","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/moonshotai/Kimi-K2.6","base_model_name":"moonshotai/Kimi-K2.6","max_context_window":262144,"input_cost":1.2,"output_cost":4.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"together_ai/moonshotai/Kimi-K2.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/moonshotai/Kimi-K2.7-Code","base_model_name":"together_ai/moonshotai/Kimi-K2.7-Code","max_context_window":262144,"input_cost":0.95,"output_cost":4,"cache_hit_input_cost":0.19,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.31031675103573525,"ci_lo":0.3003027179908134,"model":"kimi-k2-7-code","config":"mini_swe_agent_kimi_k2_7_code_default","n_runs":4,"source":"deep-swe","ci_half":0.005007016522460913,"harness":"mini-swe-agent","version":"v1.1","n_passed":138,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":138,"pass_at_1":0.3053097345132743,"pass_at_4":0.6106194690265486,"pass_rate":0.3053097345132743,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.815536243274336,"n_tasks_in_set":113,"median_cost_usd":2.1955079100000003,"mean_agent_steps":149.1150442477876,"reasoning_effort":null,"mean_cache_tokens":12857596.451327434,"mean_input_tokens":13008041.482300885,"n_tasks_attempted":113,"mean_output_tokens":59297.24778761062,"median_agent_steps":139,"n_tasks_passed_any":69,"median_input_tokens":10022682,"median_output_tokens":54054.5,"mean_duration_seconds":2163.7950712809734,"median_duration_seconds":1931.6495705,"median_peak_context_tokens":122628.5,"median_output_tokens_to_pass":48384}},"release_date":"2026-08-27","is_available_on_credits":false},"id":"together_ai/moonshotai/Kimi-K2.7-Code","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/moonshotai/Kimi-K3","base_model_name":"together_ai/moonshotai/Kimi-K3","max_context_window":1048576,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}},"release_date":"2026-07-26","is_available_on_credits":false},"id":"together_ai/moonshotai/Kimi-K3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","base_model_name":"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","max_context_window":32768,"input_cost":0.6,"output_cost":0.6,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-01-15","is_available_on_credits":false},"id":"together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","base_model_name":"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","max_context_window":32768,"input_cost":0.88,"output_cost":0.88,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-11-09","is_available_on_credits":false},"id":"together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/nvidia/nemotron-3-ultra-550b-a55b","base_model_name":"together_ai/nvidia/nemotron-3-ultra-550b-a55b","max_context_window":512288,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-27","is_available_on_credits":false},"id":"together_ai/nvidia/nemotron-3-ultra-550b-a55b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2","base_model_name":"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2","max_context_window":131072,"input_cost":0.060000000000000005,"output_cost":0.25,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-17","is_available_on_credits":false},"id":"together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/openai/gpt-oss-120b","base_model_name":"openai/gpt-oss-120b","max_context_window":131072,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":0.015,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-05"},"id":"together_ai/openai/gpt-oss-120b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":35.2343,"average_ttft":null,"average_latency":1.5945,"uptime_percent":100,"cache_hit_percentage":98.5714},"throughput":{"average_tps":35.2343,"average_ttft":null,"average_latency":1.5945,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/openai/gpt-oss-20b","base_model_name":"openai/gpt-oss-20b","max_context_window":131072,"input_cost":0.05,"output_cost":0.2,"cache_hit_input_cost":0.005,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-25"},"id":"together_ai/openai/gpt-oss-20b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":58.9725,"average_ttft":0.4307,"average_latency":1.8154,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":58.9725,"average_ttft":0.4307,"average_latency":1.8154,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2-1.5B-Instruct","base_model_name":"together_ai/Qwen/Qwen2-1.5B-Instruct","max_context_window":32768,"input_cost":0.02,"output_cost":0.02,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-06-07","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2-1.5B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2-72B-Instruct","base_model_name":"together_ai/Qwen/Qwen2-72B-Instruct","max_context_window":32768,"input_cost":0.9,"output_cost":0.9,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-09","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2-72B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2-VL-72B-Instruct","base_model_name":"together_ai/Qwen/Qwen2-VL-72B-Instruct","max_context_window":32768,"input_cost":1.2,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-01-09","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2-VL-72B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2.5-14B-Instruct","base_model_name":"together_ai/Qwen/Qwen2.5-14B-Instruct","max_context_window":32768,"input_cost":0.8,"output_cost":0.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-10","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2.5-14B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2.5-72B-Instruct","base_model_name":"together_ai/Qwen/Qwen2.5-72B-Instruct","max_context_window":32768,"input_cost":1.2,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-12-06","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2.5-72B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo","base_model_name":"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo","max_context_window":131072,"input_cost":1.2,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-11","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2.5-72B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo","base_model_name":"Qwen/Qwen2.5-7B-Instruct-Turbo","max_context_window":32768,"input_cost":0.3,"output_cost":0.3,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-10-11"},"id":"together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct","base_model_name":"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct","max_context_window":16384,"input_cost":0.8,"output_cost":0.8,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2024-11-14","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen2.5-Coder-32B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.7,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen2.5-VL-72B-Instruct","base_model_name":"together_ai/Qwen/Qwen2.5-VL-72B-Instruct","max_context_window":32768,"input_cost":1.95,"output_cost":8,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":["together_ai/Qwen/Qwen2.5-VL-72B-Instruct"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2025-03-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"together_ai/Qwen/Qwen2.5-VL-72B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","base_model_name":"together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","max_context_window":262144,"input_cost":2,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-23","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-Coder-Next-FP8","base_model_name":"together_ai/Qwen/Qwen3-Coder-Next-FP8","max_context_window":262144,"input_cost":0.5,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-Coder-Next-FP8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct","base_model_name":"together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct","max_context_window":262144,"input_cost":0.15,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-Next-80B-A3B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking","base_model_name":"together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking","max_context_window":262144,"input_cost":0.15,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-11","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-VL-32B-Instruct","base_model_name":"together_ai/Qwen/Qwen3-VL-32B-Instruct","max_context_window":262144,"input_cost":0.5,"output_cost":1.5,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-25","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-VL-32B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3-VL-8B-Instruct","base_model_name":"together_ai/Qwen/Qwen3-VL-8B-Instruct","max_context_window":262144,"input_cost":0.18000000000000002,"output_cost":0.68,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3-VL-8B-Instruct","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/Qwen/Qwen3.5-397B-A17B","base_model_name":"Qwen/Qwen3.5-397B-A17B","max_context_window":262144,"input_cost":0.6,"output_cost":3.6,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-29"},"id":"together_ai/Qwen/Qwen3.5-397B-A17B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/Qwen/Qwen3.5-9B","base_model_name":"Qwen/Qwen3.5-9B","max_context_window":262144,"input_cost":0.17,"output_cost":0.25,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"together_ai/Qwen/Qwen3.5-9B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":64.5404,"average_ttft":null,"average_latency":2.9383,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":64.5404,"average_ttft":null,"average_latency":2.9383,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/Qwen/Qwen3.6-Plus","base_model_name":"Qwen/Qwen3.6-Plus","max_context_window":1000000,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-28"},"id":"together_ai/Qwen/Qwen3.6-Plus","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/Qwen/Qwen3.7-Max","base_model_name":"Qwen/Qwen3.7-Max","max_context_window":1000000,"input_cost":1.5,"output_cost":4.5,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-05-21"},"id":"together_ai/Qwen/Qwen3.7-Max","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3.7-Plus","base_model_name":"together_ai/Qwen/Qwen3.7-Plus","max_context_window":1000000,"input_cost":0.32,"output_cost":1.28,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-15","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3.7-Plus","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3.8-2.4T-A95B","base_model_name":"together_ai/Qwen/Qwen3.8-2.4T-A95B","max_context_window":1010000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.25,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3.8-2.4T-A95B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/Qwen3.8-Flash","base_model_name":"together_ai/Qwen/Qwen3.8-Flash","max_context_window":1000000,"input_cost":0.09000000000000001,"output_cost":0.28200000000000003,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21","is_available_on_credits":false},"id":"together_ai/Qwen/Qwen3.8-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/Qwen/QwQ-32B","base_model_name":"together_ai/Qwen/QwQ-32B","max_context_window":131072,"input_cost":1.2,"output_cost":1.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-03-05","is_available_on_credits":false},"id":"together_ai/Qwen/QwQ-32B","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/thinkingmachines/Inkling","base_model_name":"together_ai/thinkingmachines/Inkling","max_context_window":524288,"input_cost":1,"output_cost":4.05,"cache_hit_input_cost":0.17,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"together_ai/thinkingmachines/Inkling","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/together/Tev1-4B-experimental","base_model_name":"","max_context_window":32768,"input_cost":0.041999999999999996,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-23"},"id":"together_ai/together/Tev1-4B-experimental","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-4.5-Air-FP8","base_model_name":"together_ai/zai-org/GLM-4.5-Air-FP8","max_context_window":131072,"input_cost":0.2,"output_cost":1.1,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-30","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-4.5-Air-FP8","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-4.6","base_model_name":"together_ai/zai-org/GLM-4.6","max_context_window":202752,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-23","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-4.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-4.7","base_model_name":"together_ai/zai-org/GLM-4.7","max_context_window":202752,"input_cost":0.45,"output_cost":2,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-02","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-4.7","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/zai-org/GLM-5","base_model_name":"zai-org/GLM-5","max_context_window":202752,"input_cost":1,"output_cost":3.2,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-22"},"id":"together_ai/zai-org/GLM-5","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"together_ai/zai-org/GLM-5.1","base_model_name":"zai-org/GLM-5.1","max_context_window":202752,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.25999999999999995,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-08-05"},"id":"together_ai/zai-org/GLM-5.1","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-5.2","base_model_name":"together_ai/zai-org/GLM-5.2","max_context_window":1048575,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.25999999999999995,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-08-27","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-5.2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-5.3","base_model_name":"together_ai/zai-org/GLM-5.3","max_context_window":1048575,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.25999999999999995,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-28","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-5.3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TogetherAI","provider_id":"togetherai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:52.392035Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.together.xyz/v1/models"},"kind":"host","id":"togetherai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"together_ai/zai-org/GLM-5.3-Flash","base_model_name":"together_ai/zai-org/GLM-5.3-Flash","max_context_window":1048575,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.030000000000000002,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-27","is_available_on_credits":false},"id":"together_ai/zai-org/GLM-5.3-Flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"TypeSafe","provider_id":"typesafe","extra_kwargs":{},"created_at":"2026-09-19T01:57:21.555758Z","updated_at":"2026-09-19T01:57:21.555780Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"typesafe"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"typesafe/jev-1.13.0","base_model_name":"typesafe/jev-1.13.0","max_context_window":64000,"input_cost":0.042,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-20"},"id":"typesafe/jev-1.13.0","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.0-pro-001","base_model_name":"vertex_ai_beta/gemini-1.0-pro-001","max_context_window":32760,"input_cost":0.25,"output_cost":0.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.0-pro-001"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32760,"release_date":"2023-12-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.0-pro-001","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-flash","base_model_name":"vertex_ai_beta/gemini-1.5-flash","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-flash"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-flash-001","base_model_name":"vertex_ai_beta/gemini-1.5-flash-001","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-flash-001"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-flash-001","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-flash-002","base_model_name":"vertex_ai_beta/gemini-1.5-flash-002","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-flash-002"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-09-24","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-flash-002","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-flash-8b","base_model_name":"vertex_ai_beta/gemini-1.5-flash-8b","max_context_window":1048576,"input_cost":0.0375,"output_cost":0.15,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-flash-8b"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2024-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-flash-8b","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":7.6923,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-flash-preview-0514","base_model_name":"vertex_ai_beta/gemini-1.5-flash-preview-0514","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-flash-preview-0514"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-flash-preview-0514","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-pro","base_model_name":"vertex_ai_beta/gemini-1.5-pro","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-1.5-pro-002","base_model_name":"vertex_ai_beta/gemini-1.5-pro-002","max_context_window":2800000,"input_cost":1.25,"output_cost":3.75,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-1.5-pro-002"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":2800000,"release_date":"2024-09-24","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-1.5-pro-002","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-computer-use-preview-10-2025","base_model_name":"vertex_ai_beta/gemini-2.5-computer-use-preview-10-2025","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-computer-use-preview-10-2025"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-07"},"id":"vertex_ai_beta/gemini-2.5-computer-use-preview-10-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-flash","base_model_name":"vertex_ai_beta/gemini-2.5-flash","max_context_window":1000000,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-flash"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1000000,"release_date":"2025-04-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-flash-preview-04-17","base_model_name":"vertex_ai_beta/gemini-2.5-flash-preview-04-17","max_context_window":1000000,"input_cost":0.15,"output_cost":0.6,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-flash-preview-04-17"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1000000,"release_date":"2025-04-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-flash-preview-04-17","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":7.6923,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-flash-preview-09-2025","base_model_name":"vertex_ai_beta/gemini-2.5-flash-preview-09-2025","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-flash-preview-09-2025"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2025-09-25","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-flash-preview-09-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-pro","base_model_name":"vertex_ai_beta/gemini-2.5-pro","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-03-25","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-pro-preview-03-25","base_model_name":"vertex_ai_beta/gemini-2.5-pro-preview-03-25","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-pro-preview-03-25"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-03-25","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-pro-preview-03-25","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-2.5-pro-preview-05-06","base_model_name":"vertex_ai_beta/gemini-2.5-pro-preview-05-06","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-2.5-pro-preview-05-06"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-05-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-2.5-pro-preview-05-06","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3-flash-preview","base_model_name":"vertex_ai_beta/gemini-3-flash-preview","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-3-flash-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-12-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3-flash-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3-pro-preview","base_model_name":"vertex_ai_beta/gemini-3-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-3-pro-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-11-18","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3-pro-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3.1-flash-image-preview","base_model_name":"vertex_ai_beta/gemini-3.1-flash-image-preview","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"vertex_ai_beta/gemini-3.1-flash-image-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3.1-flash-lite","base_model_name":"vertex_ai_beta/gemini-3.1-flash-lite","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3.1-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3.1-flash-lite-preview","base_model_name":"vertex_ai_beta/gemini-3.1-flash-lite-preview","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3.1-flash-lite-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3.1-pro-preview","base_model_name":"vertex_ai_beta/gemini-3.1-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2026-02-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3.1-pro-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-3.5-flash","base_model_name":"vertex_ai_beta/gemini-3.5-flash","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2026-05-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-3.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":45.4545,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":0.95,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai_beta/gemini-pro","base_model_name":"vertex_ai_beta/gemini-pro","max_context_window":32760,"input_cost":0.25,"output_cost":0.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai_beta/gemini-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":32760,"release_date":"2023-12-06","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai_beta/gemini-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-fable-5-1@default","base_model_name":"vertex_ai/claude-fable-5-1@default","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":0.25,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-fable-5-1@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-fable-5@default","base_model_name":"vertex_ai/claude-fable-5@default","max_context_window":1000000,"input_cost":10,"output_cost":50,"cache_hit_input_cost":1,"cache_creation_input_cost":12.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7315642200025008,"ci_lo":0.6666658684930744,"model":"claude-fable-5","config":"mini_swe_agent_claude_fable_5_xhigh","n_runs":4,"source":"deep-swe","ci_half":0.03244917575471319,"harness":"mini-swe-agent","version":"v1.1","n_passed":316,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":316,"pass_at_1":0.6991150442477876,"pass_at_4":0.8849557522123894,"pass_rate":0.6991150442477876,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.414521495535714,"n_tasks_in_set":113,"median_cost_usd":11.341082999999998,"mean_agent_steps":68.40044247787611,"reasoning_effort":"xhigh","mean_cache_tokens":7159496.181415929,"mean_input_tokens":7329160.601769911,"n_tasks_attempted":113,"mean_output_tokens":80352.1703539823,"median_agent_steps":61.5,"n_tasks_passed_any":100,"median_input_tokens":5337563.5,"median_output_tokens":76035.5,"mean_duration_seconds":1411.5830643938054,"median_duration_seconds":1231.553523,"median_peak_context_tokens":141254.5,"median_output_tokens_to_pass":75232}},"is_available_on_credits":false},"id":"vertex_ai/claude-fable-5@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-haiku-4-5@20251001","base_model_name":"vertex_ai/claude-haiku-4-5@20251001","max_context_window":200000,"input_cost":1,"output_cost":5,"cache_hit_input_cost":0.1,"cache_creation_input_cost":1.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-haiku-4-5@20251001","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-4-5@20251101","base_model_name":"vertex_ai/claude-opus-4-5@20251101","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-opus-4-5@20251101","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-4-6@default","base_model_name":"vertex_ai/claude-opus-4-6@default","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-opus-4-6@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Controls the randomness of the model. Lower values make the model more deterministic."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-4-7@default","base_model_name":"vertex_ai/claude-opus-4-7@default","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":200000,"release_date":"2025-05-14","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/claude-opus-4-7@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":8.2936,"average_ttft":null,"average_latency":1.9292,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":8.2936,"average_ttft":null,"average_latency":1.9292,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-4-8@default","base_model_name":"vertex_ai/claude-opus-4-8@default","max_context_window":200000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6073917432178823,"ci_lo":0.5720954362692973,"model":"claude-opus-4-8","config":"mini_swe_agent_claude_opus_4_8_max","n_runs":4,"source":"deep-swe","ci_half":0.01764815347429254,"harness":"mini-swe-agent","version":"v1.1","n_passed":253,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":253,"pass_at_1":0.5897435897435898,"pass_at_4":0.7927927927927928,"pass_rate":0.5897435897435898,"n_attempted":429,"ci_attempted":429,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":13.222583593240094,"n_tasks_in_set":113,"median_cost_usd":12.353505999999996,"mean_agent_steps":120,"reasoning_effort":"max","mean_cache_tokens":16817766.494172495,"mean_input_tokens":17047938.554778554,"n_tasks_attempted":111,"mean_output_tokens":135031.67132867133,"median_agent_steps":116,"n_tasks_passed_any":88,"median_input_tokens":15368311,"median_output_tokens":129180,"mean_duration_seconds":3492.740812641026,"median_duration_seconds":2883.384473,"median_peak_context_tokens":225741,"median_output_tokens_to_pass":125257}},"context_size":200000,"release_date":"2026-05-28","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/claude-opus-4-8@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-5-5@default","base_model_name":"vertex_ai/claude-opus-5-5@default","max_context_window":1000000,"input_cost":4,"output_cost":20,"cache_hit_input_cost":0.2,"cache_creation_input_cost":5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-opus-5-5@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-opus-5@default","base_model_name":"vertex_ai/claude-opus-5@default","max_context_window":1000000,"input_cost":5,"output_cost":25,"cache_hit_input_cost":0.5,"cache_creation_input_cost":6.25,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7752095907502038,"ci_lo":0.6977633822227692,"model":"claude-opus-5","config":"mini_swe_agent_claude_opus_5_max","n_runs":4,"source":"deep-swe","ci_half":0.03872310426371729,"harness":"mini-swe-agent","version":"v1.1","n_passed":327,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":327,"pass_at_1":0.7364864864864865,"pass_at_4":0.8849557522123894,"pass_rate":0.7364864864864865,"n_attempted":444,"ci_attempted":444,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":11.837583271396396,"n_tasks_in_set":113,"median_cost_usd":10.4281505,"mean_agent_steps":99.0427927927928,"reasoning_effort":"max","mean_cache_tokens":14784785.963963963,"mean_input_tokens":15025834.39864865,"n_tasks_attempted":113,"mean_output_tokens":117565.6936936937,"median_agent_steps":90.5,"n_tasks_passed_any":100,"median_input_tokens":12130307.5,"median_output_tokens":113366.5,"mean_duration_seconds":1911.819866231982,"median_duration_seconds":1801.1237265,"median_peak_context_tokens":215810,"median_output_tokens_to_pass":112874}},"is_available_on_credits":false},"id":"vertex_ai/claude-opus-5@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-sonnet-4-6@default","base_model_name":"vertex_ai/claude-sonnet-4-6@default","max_context_window":200000,"input_cost":3,"output_cost":15,"cache_hit_input_cost":0.3,"cache_creation_input_cost":3.75,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.34025622422182483,"ci_lo":0.2584133988380421,"model":"claude-sonnet-4-6","config":"mini_swe_agent_claude_sonnet_4_6_high","n_runs":4,"source":"deep-swe","ci_half":0.04092141269189136,"harness":"mini-swe-agent","version":"v1.1","n_passed":135,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":135,"pass_at_1":0.29933481152993346,"pass_at_4":0.5663716814159292,"pass_rate":0.29933481152993346,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":5.5223517987804875,"n_tasks_in_set":113,"median_cost_usd":4.867440150000001,"mean_agent_steps":133.65853658536585,"reasoning_effort":"high","mean_cache_tokens":12719994.494456762,"mean_input_tokens":12870627.738359202,"n_tasks_attempted":113,"mean_output_tokens":76160.31263858093,"median_agent_steps":124,"n_tasks_passed_any":64,"median_input_tokens":10933709,"median_output_tokens":70001,"mean_duration_seconds":2815.01307943459,"median_duration_seconds":2373.991057,"median_peak_context_tokens":146430,"median_output_tokens_to_pass":67060}},"is_available_on_credits":false},"id":"vertex_ai/claude-sonnet-4-6@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-sonnet-5-5@default","base_model_name":"vertex_ai/claude-sonnet-5-5@default","max_context_window":1000000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/claude-sonnet-5-5@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/claude-sonnet-5@default","base_model_name":"vertex_ai/claude-sonnet-5@default","max_context_window":200000,"input_cost":2,"output_cost":10,"cache_hit_input_cost":0.2,"cache_creation_input_cost":2.5,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5808307031632823,"ci_lo":0.4960923737597946,"model":"claude-sonnet-5","config":"mini_swe_agent_claude_sonnet_5_max","n_runs":4,"source":"deep-swe","ci_half":0.04236916470174386,"harness":"mini-swe-agent","version":"v1.1","n_passed":238,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":238,"pass_at_1":0.5384615384615384,"pass_at_4":0.7876106194690266,"pass_rate":0.5384615384615384,"n_attempted":442,"ci_attempted":442,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":26.399858950791852,"n_tasks_in_set":113,"median_cost_usd":23.277376725000003,"mean_agent_steps":268.4547511312217,"reasoning_effort":"max","mean_cache_tokens":71991474.90950227,"mean_input_tokens":72415756.48642534,"n_tasks_attempted":113,"mean_output_tokens":214117.54977375566,"median_agent_steps":260,"n_tasks_passed_any":89,"median_input_tokens":62591138,"median_output_tokens":203917.5,"mean_duration_seconds":4803.543157789592,"median_duration_seconds":4345.498858000001,"median_peak_context_tokens":409978.5,"median_output_tokens_to_pass":203255.5}},"is_available_on_credits":false},"id":"vertex_ai/claude-sonnet-5@default","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/deepseek-ai/deepseek-r1-0528-maas","base_model_name":"vertex_ai/deepseek-ai/deepseek-r1-0528-maas","max_context_window":163840,"input_cost":1.35,"output_cost":5.4,"cache_hit_input_cost":1.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/deepseek-ai/deepseek-r1-0528-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/deepseek-ai/deepseek-v3.1-maas","base_model_name":"vertex_ai/deepseek-ai/deepseek-v3.1-maas","max_context_window":163840,"input_cost":0.6,"output_cost":1.7,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/deepseek-ai/deepseek-v3.1-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/deepseek-ai/deepseek-v3.2-maas","base_model_name":"deepseek-ai/deepseek-v3.2-maas","max_context_window":163840,"input_cost":0.56,"output_cost":1.68,"cache_hit_input_cost":0.056,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"vertex_ai/deepseek-ai/deepseek-v3.2-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-2.5-computer-use-preview-10-2025","base_model_name":"vertex_ai/gemini-2.5-computer-use-preview-10-2025","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai/gemini-2.5-computer-use-preview-10-2025"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-10-07"},"id":"vertex_ai/gemini-2.5-computer-use-preview-10-2025","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-2.5-flash","base_model_name":"vertex_ai/gemini-2.5-flash","max_context_window":1000000,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai/gemini-2.5-flash"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1000000,"release_date":"2025-04-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-2.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":7.6923,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-2.5-flash-lite","base_model_name":"vertex_ai/gemini-2.5-flash-lite","max_context_window":1048576,"input_cost":0.1,"output_cost":0.4,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-06-17","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-2.5-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":7.6923,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-2.5-pro","base_model_name":"vertex_ai/gemini-2.5-pro","max_context_window":1048576,"input_cost":1.25,"output_cost":10,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai/gemini-2.5-pro"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2025-03-25","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-2.5-pro","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3-pro-preview","base_model_name":"vertex_ai/gemini-3-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":["vertex_ai/gemini-3-pro-preview"],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2025-11-18","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-3-pro-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.1-flash-image-preview","base_model_name":"vertex_ai/gemini-3.1-flash-image-preview","max_context_window":1048576,"input_cost":0.5,"output_cost":3,"cache_hit_input_cost":-1,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-26"},"id":"vertex_ai/gemini-3.1-flash-image-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.1-flash-lite","base_model_name":"vertex_ai/gemini-3.1-flash-lite","max_context_window":1048576,"input_cost":0.25,"output_cost":1.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":1048576,"release_date":"2026-03-03","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-3.1-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for repeating tokens."},"presence_penalty":{"name":"presence_penalty","type":"number","range":{"max":1.999,"min":-2},"default":0,"required":false,"description":"The penalty for tokens that are already in the text."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.1-pro-preview","base_model_name":"vertex_ai/gemini-3.1-pro-preview","max_context_window":1048576,"input_cost":2,"output_cost":12,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.13206759177923005,"ci_lo":0.10244568255705315,"model":"gemini-3-1-pro-preview","config":"mini_swe_agent_gemini_3_1_pro_preview_high","n_runs":4,"source":"deep-swe","ci_half":0.01481095461108845,"harness":"mini-swe-agent","version":"v1.1","n_passed":53,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":53,"pass_at_1":0.1172566371681416,"pass_at_4":0.2831858407079646,"pass_rate":0.1172566371681416,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-03T22:24:37.984682+00:00","mean_cost_usd":2.1434045568888886,"n_tasks_in_set":113,"median_cost_usd":1.7235064000000002,"mean_agent_steps":75.56444444444445,"reasoning_effort":"high","mean_cache_tokens":1678992.7311111111,"mean_input_tokens":2403677.331111111,"n_tasks_attempted":113,"mean_output_tokens":28368.884444444444,"median_agent_steps":70,"n_tasks_passed_any":32,"median_input_tokens":1834116,"median_output_tokens":25990.5,"mean_duration_seconds":867.7979107013274,"median_duration_seconds":734.5636605,"median_peak_context_tokens":49745.5,"median_output_tokens_to_pass":23839}},"context_size":1048576,"release_date":"2026-02-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-3.1-pro-preview","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.5-flash","base_model_name":"vertex_ai/gemini-3.5-flash","max_context_window":1048576,"input_cost":1.5,"output_cost":9,"cache_hit_input_cost":0.15,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.40028249913175307,"ci_lo":0.3209564389213443,"model":"gemini-3-5-flash","config":"mini_swe_agent_gemini_3_5_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.03966303010520439,"harness":"mini-swe-agent","version":"v1.1","n_passed":163,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":163,"pass_at_1":0.3606194690265487,"pass_at_4":0.6371681415929203,"pass_rate":0.3606194690265487,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4467114588691796,"n_tasks_in_set":113,"median_cost_usd":2.8624087500000015,"mean_agent_steps":105.30376940133037,"reasoning_effort":"high","mean_cache_tokens":6428494.862527716,"mean_input_tokens":7629071.858093127,"n_tasks_attempted":113,"mean_output_tokens":75730.19290465632,"median_agent_steps":97,"n_tasks_passed_any":72,"median_input_tokens":5694082,"median_output_tokens":68910,"mean_duration_seconds":1125.1601607057523,"median_duration_seconds":973.6770345,"median_peak_context_tokens":113979,"median_output_tokens_to_pass":64913}},"context_size":1048576,"release_date":"2026-05-19","prompt_logging":true,"prompt_training":false,"zero_data_retention":true,"stream_cancellation_supported":true},"id":"vertex_ai/gemini-3.5-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":53.5043,"average_ttft":null,"average_latency":1.4018,"uptime_percent":11.1111,"cache_hit_percentage":0},"throughput":{"average_tps":53.5043,"average_ttft":null,"average_latency":1.4018,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.5-flash-lite","base_model_name":"vertex_ai/gemini-3.5-flash-lite","max_context_window":1048576,"input_cost":0.3,"output_cost":2.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/gemini-3.5-flash-lite","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.6-flash","base_model_name":"vertex_ai/gemini-3.6-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5038626982845081,"ci_lo":0.4297656202995626,"model":"gemini-3-6-flash","config":"mini_swe_agent_gemini_3_6_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.037048538992472776,"harness":"mini-swe-agent","version":"v1.1","n_passed":211,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":211,"pass_at_1":0.4668141592920354,"pass_at_4":0.7522123893805309,"pass_rate":0.4668141592920354,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.419013277333334,"n_tasks_in_set":113,"median_cost_usd":3.444695325000001,"mean_agent_steps":116.73333333333333,"reasoning_effort":"high","mean_cache_tokens":11254636.448888889,"mean_input_tokens":12595957.344444444,"n_tasks_attempted":113,"mean_output_tokens":95844.86222222222,"median_agent_steps":108,"n_tasks_passed_any":85,"median_input_tokens":8949018.5,"median_output_tokens":86727,"mean_duration_seconds":1477.8607510707964,"median_duration_seconds":1214.8670550000002,"median_peak_context_tokens":151398.5,"median_output_tokens_to_pass":83414}},"is_available_on_credits":false},"id":"vertex_ai/gemini-3.6-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.7-flash","base_model_name":"vertex_ai/gemini-3.7-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6857325794013234,"ci_lo":0.624001933873013,"model":"gemini-3-7-flash","config":"mini_swe_agent_gemini_3_7_flash_medium","n_runs":4,"source":"deep-swe","ci_half":0.030865322764155222,"harness":"mini-swe-agent","version":"v1.1","n_passed":296,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":296,"pass_at_1":0.6548672566371682,"pass_at_4":0.831858407079646,"pass_rate":0.6548672566371682,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.0251351826880533,"n_tasks_in_set":113,"median_cost_usd":1.65422055,"mean_agent_steps":117.36946902654867,"reasoning_effort":"medium","mean_cache_tokens":14557599.913716814,"mean_input_tokens":15332065.907079646,"n_tasks_attempted":113,"mean_output_tokens":93990.8517699115,"median_agent_steps":108,"n_tasks_passed_any":94,"median_input_tokens":11116142,"median_output_tokens":87640.5,"mean_duration_seconds":1240.376194079646,"median_duration_seconds":1066.1105834999998,"median_peak_context_tokens":195705.5,"median_output_tokens_to_pass":87132.5}},"is_available_on_credits":false},"id":"vertex_ai/gemini-3.7-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/gemini-3.8-flash","base_model_name":"vertex_ai/gemini-3.8-flash","max_context_window":1048576,"input_cost":0.75,"output_cost":3.75,"cache_hit_input_cost":0.075,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7524281656234058,"ci_lo":0.7240819014906883,"model":"gemini-3-8-flash","config":"mini_swe_agent_gemini_3_8_flash_high","n_runs":4,"source":"deep-swe","ci_half":0.014173132066358783,"harness":"mini-swe-agent","version":"v1.1","n_passed":330,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":330,"pass_at_1":0.738255033557047,"pass_at_4":0.8584070796460177,"pass_rate":0.738255033557047,"n_attempted":447,"ci_attempted":447,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.362349413758389,"n_tasks_in_set":113,"median_cost_usd":2.1098912999999997,"mean_agent_steps":166.3131991051454,"reasoning_effort":"high","mean_cache_tokens":21456039.230425056,"mean_input_tokens":21734449.25279642,"n_tasks_attempted":113,"mean_output_tokens":143242.6644295302,"median_agent_steps":161,"n_tasks_passed_any":97,"median_input_tokens":18026661,"median_output_tokens":138377,"mean_duration_seconds":686.7691519843399,"median_duration_seconds":604.643838,"median_peak_context_tokens":215558,"median_output_tokens_to_pass":136617.5}},"is_available_on_credits":false},"id":"vertex_ai/gemini-3.8-flash","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":0,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/meta/llama-3.3-70b-instruct-maas","base_model_name":"vertex_ai/meta/llama-3.3-70b-instruct-maas","max_context_window":131072,"input_cost":0.72,"output_cost":0.72,"cache_hit_input_cost":0.72,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/meta/llama-3.3-70b-instruct-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","base_model_name":"vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","max_context_window":1048576,"input_cost":0.35,"output_cost":1.15,"cache_hit_input_cost":0.35,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/minimaxai/minimax-m2-maas","base_model_name":"vertex_ai/minimaxai/minimax-m2-maas","max_context_window":204800,"input_cost":0.3,"output_cost":1.2,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/minimaxai/minimax-m2-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/mistralai/codestral-2","base_model_name":"vertex_ai/mistralai/codestral-2","max_context_window":256000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/mistralai/codestral-2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/mistralai/mistral-medium-3","base_model_name":"vertex_ai/mistralai/mistral-medium-3","max_context_window":131072,"input_cost":0.4,"output_cost":2,"cache_hit_input_cost":0.4,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/mistralai/mistral-medium-3","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/mistralai/mistral-small-2503","base_model_name":"vertex_ai/mistralai/mistral-small-2503","max_context_window":131072,"input_cost":0.1,"output_cost":0.3,"cache_hit_input_cost":0.1,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/mistralai/mistral-small-2503","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/moonshotai/kimi-k2-thinking-maas","base_model_name":"moonshotai/kimi-k2-thinking-maas","max_context_window":262144,"input_cost":0.6,"output_cost":2.5,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-11"},"id":"vertex_ai/moonshotai/kimi-k2-thinking-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/openai/gpt-oss-120b-maas","base_model_name":"vertex_ai/openai/gpt-oss-120b-maas","max_context_window":131072,"input_cost":0.09,"output_cost":0.36,"cache_hit_input_cost":0.09,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/openai/gpt-oss-120b-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas","base_model_name":"qwen/qwen3-235b-a22b-instruct-2507-maas","max_context_window":262144,"input_cost":0.22,"output_cost":0.88,"cache_hit_input_cost":0.22,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas","base_model_name":"qwen/qwen3-coder-480b-a35b-instruct-maas","max_context_window":262144,"input_cost":0.22,"output_cost":1.8,"cache_hit_input_cost":0.022,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas","base_model_name":"qwen/qwen3-next-80b-a3b-instruct-maas","max_context_window":262144,"input_cost":0.15,"output_cost":1.2,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas","base_model_name":"qwen/qwen3-next-80b-a3b-thinking-maas","max_context_window":262144,"input_cost":0.15,"output_cost":1.2,"cache_hit_input_cost":0.15,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-04-29"},"id":"vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":null,"average_ttft":null,"average_latency":null,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":null,"average_ttft":null,"average_latency":null,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/xai/grok-4.20-non-reasoning","base_model_name":"vertex_ai/xai/grok-4.20-non-reasoning","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/xai/grok-4.20-non-reasoning","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/xai/grok-4.20-reasoning","base_model_name":"vertex_ai/xai/grok-4.20-reasoning","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/xai/grok-4.20-reasoning","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/xai/grok-4.6","base_model_name":"vertex_ai/xai/grok-4.6","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.697586806790726,"ci_lo":0.6519707153331677,"model":"grok-4-6","config":"mini_swe_agent_grok_4_6_medium","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":305,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":305,"pass_at_1":0.6747787610619469,"pass_at_4":0.8407079646017699,"pass_rate":0.6747787610619469,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4489837522123894,"n_tasks_in_set":113,"median_cost_usd":2.945834,"mean_agent_steps":70.28982300884955,"reasoning_effort":"medium","mean_cache_tokens":5533327.0088495575,"mean_input_tokens":5725195.139380531,"n_tasks_attempted":113,"mean_output_tokens":49763.99778761062,"median_agent_steps":66,"n_tasks_passed_any":95,"median_input_tokens":4705124,"median_output_tokens":48585.5,"mean_duration_seconds":895.5380579646018,"median_duration_seconds":860.0352045,"median_peak_context_tokens":116622,"median_output_tokens_to_pass":48346}},"is_available_on_credits":false},"id":"vertex_ai/xai/grok-4.6","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Google Vertex AI","provider_id":"google_vertex_ai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:51.147313Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://us-central1-aiplatform.googleapis.com/v1beta1/publishers/*/models"},"kind":"host","id":"google_vertex_ai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"vertex_ai/zai-org/glm-4.7-maas","base_model_name":"vertex_ai/zai-org/glm-4.7-maas","max_context_window":204800,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.06,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability.function_call","capability.vision","cost_tiers","input_cost","max_context_window","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"is_available_on_credits":false},"id":"vertex_ai/zai-org/glm-4.7-maas","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/DeepSeek-V4-Flash-0731-Fast","base_model_name":"","max_context_window":1048576,"input_cost":0.05,"output_cost":0.29,"cache_hit_input_cost":0.0439,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"wafer/DeepSeek-V4-Flash-0731-Fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":31.4835,"average_ttft":null,"average_latency":1.3976,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":31.4835,"average_ttft":null,"average_latency":1.3976,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/DeepSeek-V4-Pro","base_model_name":"wafer/DeepSeek-V4-Pro","max_context_window":1048576,"input_cost":0.39,"output_cost":3.49,"cache_hit_input_cost":0.3159,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["cache_creation_input_cost","cache_hit_input_cost","capability","capability.function_call","capability.vision","cost_tiers","display_name","input_cost","max_context_window","metadata","model_type","output_cost","time_cost_schedule"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6916528900430852,"ci_lo":0.5649842780985077,"model":"deepseek-v4-pro","config":"mini_swe_agent_deepseek_v4_pro_max","n_runs":4,"source":"deep-swe","ci_half":0.06333430597228876,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6283185840707964,"pass_at_4":0.8849557522123894,"pass_rate":0.6283185840707964,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.24138687892256638,"n_tasks_in_set":113,"median_cost_usd":0.2232531505000001,"mean_agent_steps":154.71238938053096,"reasoning_effort":"max","mean_cache_tokens":24049100.743362833,"mean_input_tokens":24191606.099557523,"n_tasks_attempted":113,"mean_output_tokens":105998.91814159292,"median_agent_steps":146,"n_tasks_passed_any":100,"median_input_tokens":20628260.5,"median_output_tokens":101213.5,"mean_duration_seconds":2212.510104011062,"median_duration_seconds":2104.8520015000004,"median_peak_context_tokens":232374.5,"median_output_tokens_to_pass":100505.5}},"release_date":"2026-04-24"},"id":"wafer/DeepSeek-V4-Pro","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/DeepSeek-V4.1-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.1,"output_cost":0.44,"cache_hit_input_cost":0.045,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"wafer/DeepSeek-V4.1-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/GLM-5.2","base_model_name":"","max_context_window":1048576,"input_cost":0.23,"output_cost":4.4,"cache_hit_input_cost":0.1871,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}}},"id":"wafer/GLM-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/GLM-5.3","base_model_name":"","max_context_window":1048576,"input_cost":0.22,"output_cost":3.39,"cache_hit_input_cost":0.1775,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}}},"id":"wafer/GLM-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":160.092,"average_ttft":2.6426,"average_latency":6.5387,"uptime_percent":100,"cache_hit_percentage":86.0695},"throughput":{"average_tps":160.092,"average_ttft":2.6426,"average_latency":6.5387,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/GLM-5.3-Flash","base_model_name":"","max_context_window":1048576,"input_cost":0.75,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}}},"id":"wafer/GLM-5.3-Flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/Kimi-K3","base_model_name":"","max_context_window":1048576,"input_cost":1.44,"output_cost":9,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7305142649613376,"ci_lo":0.6397739833756912,"model":"kimi-k3","config":"mini_swe_agent_kimi_k3_max","n_runs":4,"source":"deep-swe","ci_half":0.045370140792823206,"harness":"mini-swe-agent","version":"v1.1","n_passed":309,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":309,"pass_at_1":0.6851441241685144,"pass_at_4":0.8938053097345132,"pass_rate":0.6851441241685144,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":4.654682129933482,"n_tasks_in_set":113,"median_cost_usd":3.6024987,"mean_agent_steps":97.58758314855876,"reasoning_effort":"max","mean_cache_tokens":9501527.498891352,"mean_input_tokens":9695436.246119734,"n_tasks_attempted":113,"mean_output_tokens":81499.84257206209,"median_agent_steps":88,"n_tasks_passed_any":101,"median_input_tokens":6930356,"median_output_tokens":75383,"mean_duration_seconds":4541.447376412417,"median_duration_seconds":3972.857633,"median_peak_context_tokens":130945,"median_output_tokens_to_pass":74586}}},"id":"wafer/Kimi-K3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Wafer","provider_id":"wafer","extra_kwargs":{},"created_at":"2026-06-09T02:34:28.695379Z","updated_at":"2026-06-09T02:34:28.695398Z","respan_discount_rate":0,"models_sync_config":{"auth_type":"none","is_scheduled":true,"list_endpoint":"https://pass.wafer.ai/v1/models"},"kind":"host","id":"wafer"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"wafer/Qwen3.8-27B","base_model_name":"","max_context_window":262144,"input_cost":0.02,"output_cost":4.4,"cache_hit_input_cost":0.0199,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{},"id":"wafer/Qwen3.8-27B","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.7374,"average_ttft":null,"average_latency":0.8924,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":34.7374,"average_ttft":null,"average_latency":0.8924,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-0309","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-0309","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"xai/grok-4.20-0309-non-reasoning","base_model_name":"grok-4.20-0309-non-reasoning","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-0309-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":17.1058,"average_ttft":null,"average_latency":0.4701,"uptime_percent":100,"cache_hit_percentage":69.1892},"throughput":{"average_tps":17.1058,"average_ttft":null,"average_latency":0.4701,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"xai/grok-4.20-0309-reasoning","base_model_name":"grok-4.20-0309-reasoning","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-0309-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":103.051,"average_ttft":null,"average_latency":2.2002,"uptime_percent":100,"cache_hit_percentage":68.4492},"throughput":{"average_tps":103.051,"average_ttft":null,"average_latency":2.2002,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-0309","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-0309","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-0309-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-0309-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-0309-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-0309-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-latest-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-latest-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-latest-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-latest-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-beta-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-beta-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-0304","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-0304","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-0304-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-0304-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-0304-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-0304-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-non-reasoning-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-non-reasoning-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-experimental-beta-reasoning-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-experimental-beta-reasoning-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"xai/grok-4.20-multi-agent-0309","base_model_name":"grok-4.20-multi-agent-0309","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-0309","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":408.6093,"average_ttft":null,"average_latency":5.1834,"uptime_percent":100,"cache_hit_percentage":77.254},"throughput":{"average_tps":408.6093,"average_ttft":null,"average_latency":5.1834,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent-beta-0309","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-beta-0309","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent-beta-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-beta-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent-experimental-beta-0304","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-experimental-beta-0304","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent-experimental-beta-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-experimental-beta-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-multi-agent-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-multi-agent-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-non-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-non-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-non-reasoning-gv2","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-non-reasoning-gv2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-non-reasoning-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-non-reasoning-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-reasoning","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-reasoning","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-reasoning-gv2","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-reasoning-gv2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.20-reasoning-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-03-09"},"id":"xai/grok-4.20-reasoning-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.3","base_model_name":"xai/grok-4.3","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-17"},"id":"xai/grok-4.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":73.5787,"average_ttft":null,"average_latency":2.2097,"uptime_percent":100,"cache_hit_percentage":99.4819},"throughput":{"average_tps":73.5787,"average_ttft":null,"average_latency":2.2097,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.3-latest","base_model_name":"","max_context_window":1000000,"input_cost":1.25,"output_cost":2.5,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-17"},"id":"xai/grok-4.3-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.5","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.5604186651978057,"ci_lo":0.5148025737402474,"model":"grok-4-5","config":"mini_swe_agent_grok_4_5_high","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":243,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":243,"pass_at_1":0.5376106194690266,"pass_at_4":0.7787610619469026,"pass_rate":0.5376106194690266,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":2.4157481725663716,"n_tasks_in_set":113,"median_cost_usd":2.02311,"mean_agent_steps":61.33185840707964,"reasoning_effort":"high","mean_cache_tokens":3943846.5132743362,"mean_input_tokens":4059182.975663717,"n_tasks_attempted":113,"mean_output_tokens":35525.33185840708,"median_agent_steps":56,"n_tasks_passed_any":88,"median_input_tokens":3293744.5,"median_output_tokens":34250,"mean_duration_seconds":484.7029359800885,"median_duration_seconds":430.0852805,"median_peak_context_tokens":94044,"median_output_tokens_to_pass":33872}},"release_date":"2026-07-16"},"id":"xai/grok-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.5-latest","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-29"},"id":"xai/grok-4.5-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.6","base_model_name":"xai/grok-4.6","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.697586806790726,"ci_lo":0.6519707153331677,"model":"grok-4-6","config":"mini_swe_agent_grok_4_6_medium","n_runs":4,"source":"deep-swe","ci_half":0.0228080457287792,"harness":"mini-swe-agent","version":"v1.1","n_passed":305,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":305,"pass_at_1":0.6747787610619469,"pass_at_4":0.8407079646017699,"pass_rate":0.6747787610619469,"n_attempted":452,"ci_attempted":452,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.4489837522123894,"n_tasks_in_set":113,"median_cost_usd":2.945834,"mean_agent_steps":70.28982300884955,"reasoning_effort":"medium","mean_cache_tokens":5533327.0088495575,"mean_input_tokens":5725195.139380531,"n_tasks_attempted":113,"mean_output_tokens":49763.99778761062,"median_agent_steps":66,"n_tasks_passed_any":95,"median_input_tokens":4705124,"median_output_tokens":48585.5,"mean_duration_seconds":895.5380579646018,"median_duration_seconds":860.0352045,"median_peak_context_tokens":116622,"median_output_tokens_to_pass":48346}},"release_date":"2026-08-12","is_available_on_credits":true},"id":"xai/grok-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":34.569,"average_ttft":null,"average_latency":1.8051,"uptime_percent":100,"cache_hit_percentage":80.3768},"throughput":{"average_tps":34.569,"average_ttft":null,"average_latency":1.8051,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-4.7","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.5,"cache_creation_input_cost":0,"respan_discount_rate":0.2,"overridden_fields":["metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-09-21"},"id":"xai/grok-4.7","is_byok":false,"effective_discount_rate":0.2,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-build-0.1","base_model_name":"xai/grok-build-0.1","max_context_window":256000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":-1,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"xai/grok-build-0.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":1,"metrics":{"average_tps":67.1435,"average_ttft":null,"average_latency":3.0231,"uptime_percent":100,"cache_hit_percentage":67.7249},"throughput":{"average_tps":67.1435,"average_ttft":null,"average_latency":3.0231,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-build-latest","base_model_name":"","max_context_window":500000,"input_cost":2,"output_cost":6,"cache_hit_input_cost":0.3,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-06-29"},"id":"xai/grok-build-latest","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-code-fast","base_model_name":"","max_context_window":256000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"xai/grok-code-fast","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":133.5951,"average_ttft":null,"average_latency":2.0708,"uptime_percent":100,"cache_hit_percentage":84.2105},"throughput":{"average_tps":133.5951,"average_ttft":null,"average_latency":2.0708,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-code-fast-1","base_model_name":"","max_context_window":256000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"xai/grok-code-fast-1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"xAI","provider_id":"xai","extra_kwargs":{},"created_at":null,"updated_at":"2026-06-06T01:26:54.878026Z","respan_discount_rate":0,"models_sync_config":{"is_scheduled":true,"list_endpoint":"https://api.x.ai/v1/models"},"kind":"host","id":"xai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"xai/grok-code-fast-1-0825","base_model_name":"","max_context_window":256000,"input_cost":1,"output_cost":2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-16"},"id":"xai/grok-code-fast-1-0825","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":0,"image_support":1,"enforce_function_call":0,"metrics":null,"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Yutori","provider_id":"yutori","extra_kwargs":{},"created_at":"2026-08-28T04:38:00.352199Z","updated_at":"2026-08-28T04:38:00.352220Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"yutori"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":0.6,"required":false,"description":"Controls sampling randomness. Yutori n2 rejects temperature 0."},"top_p":{"name":"top_p","type":"number","default":0.95,"required":false,"description":"Controls nucleus sampling."},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"reasoning_effort":{"name":"reasoning_effort","type":"string","default":"medium","required":false,"description":"Reasoning effort: none, low, medium, or xhigh."},"max_completion_tokens":{"name":"max_completion_tokens","type":"int","default":16384,"required":false,"description":"Maximum tokens shared by the reasoning trace and tool-call output."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"yutori/n2","base_model_name":"n2","max_context_window":128000,"input_cost":0.5,"output_cost":4,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"context_size":128000,"release_date":"2026-08-26","is_available_on_credits":false},"id":"yutori/n2","is_byok":true,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":5.906,"average_ttft":null,"average_latency":0.6773,"uptime_percent":100,"cache_hit_percentage":86.9421},"throughput":{"average_tps":5.906,"average_ttft":null,"average_latency":0.6773,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.5","base_model_name":"glm-4.5","max_context_window":128000,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"zai/glm-4.5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.3117,"average_ttft":null,"average_latency":14.2655,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.3117,"average_ttft":null,"average_latency":14.2655,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.5-air","base_model_name":"glm-4.5-air","max_context_window":128000,"input_cost":0.2,"output_cost":1.1,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"zai/glm-4.5-air","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":24.1536,"average_ttft":null,"average_latency":1.3121,"uptime_percent":100,"cache_hit_percentage":40},"throughput":{"average_tps":24.1536,"average_ttft":null,"average_latency":1.3121,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.5-airx","base_model_name":"glm-4.5-airx","max_context_window":128000,"input_cost":1.1,"output_cost":4.5,"cache_hit_input_cost":0.22,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"zai/glm-4.5-airx","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":39.6106,"average_ttft":null,"average_latency":1.6197,"uptime_percent":100,"cache_hit_percentage":75},"throughput":{"average_tps":39.6106,"average_ttft":null,"average_latency":1.6197,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.5-flash","base_model_name":"glm-4.5-flash","max_context_window":200000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"zai/glm-4.5-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":23.2012,"average_ttft":null,"average_latency":129.0298,"uptime_percent":100,"cache_hit_percentage":10.3061},"throughput":{"average_tps":23.2012,"average_ttft":null,"average_latency":0.1290298,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.5-x","base_model_name":"glm-4.5-x","max_context_window":128000,"input_cost":2.2,"output_cost":8.9,"cache_hit_input_cost":0.45,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-07-28"},"id":"zai/glm-4.5-x","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":37.4459,"average_ttft":null,"average_latency":5.8484,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":37.4459,"average_ttft":null,"average_latency":5.8484,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":0.6,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-4.5v","base_model_name":"zai/glm-4.5v","max_context_window":64000,"input_cost":0.6,"output_cost":1.8,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-08-11"},"id":"zai/glm-4.5v","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":23.7261,"average_ttft":null,"average_latency":2.4824,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":23.7261,"average_ttft":null,"average_latency":2.4824,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.6","base_model_name":"glm-4.6","max_context_window":200000,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-09-30"},"id":"zai/glm-4.6","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":38.8132,"average_ttft":null,"average_latency":6.0053,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":38.8132,"average_ttft":null,"average_latency":6.0053,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-4.6v","base_model_name":"zai/glm-4.6v","max_context_window":128000,"input_cost":0.3,"output_cost":0.9,"cache_hit_input_cost":0.05,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-08"},"id":"zai/glm-4.6v","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":33.9508,"average_ttft":null,"average_latency":1.7542,"uptime_percent":100,"cache_hit_percentage":57.1429},"throughput":{"average_tps":33.9508,"average_ttft":null,"average_latency":1.7542,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-4.6v-flash","base_model_name":"zai/glm-4.6v-flash","max_context_window":128000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-08"},"id":"zai/glm-4.6v-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":13.7242,"average_ttft":null,"average_latency":7.0352,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":13.7242,"average_ttft":null,"average_latency":7.0352,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-4.6v-flashx","base_model_name":"zai/glm-4.6v-flashx","max_context_window":128000,"input_cost":0.04,"output_cost":0.4,"cache_hit_input_cost":0.004,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-08"},"id":"zai/glm-4.6v-flashx","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":35.7907,"average_ttft":null,"average_latency":1.4985,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":35.7907,"average_ttft":null,"average_latency":1.4985,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.7","base_model_name":"glm-4.7","max_context_window":200000,"input_cost":0.6,"output_cost":2.2,"cache_hit_input_cost":0.11,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"zai/glm-4.7","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":130.3891,"average_ttft":4.8114,"average_latency":6.121,"uptime_percent":100,"cache_hit_percentage":3.9506},"throughput":{"average_tps":130.3891,"average_ttft":4.8114,"average_latency":6.121,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.7-flash","base_model_name":"glm-4.7-flash","max_context_window":200000,"input_cost":0,"output_cost":0,"cache_hit_input_cost":0,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"zai/glm-4.7-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.3777,"average_ttft":null,"average_latency":31.0743,"uptime_percent":100,"cache_hit_percentage":0.2179},"throughput":{"average_tps":26.3777,"average_ttft":null,"average_latency":31.0743,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-4.7-flashx","base_model_name":"glm-4.7-flashx","max_context_window":200000,"input_cost":0.07,"output_cost":0.4,"cache_hit_input_cost":0.01,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2025-12-22"},"id":"zai/glm-4.7-flashx","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":30.9627,"average_ttft":null,"average_latency":4.506,"uptime_percent":100,"cache_hit_percentage":41.6667},"throughput":{"average_tps":30.9627,"average_ttft":null,"average_latency":4.506,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-5","base_model_name":"glm-5","max_context_window":200000,"input_cost":1,"output_cost":3.2,"cache_hit_input_cost":0.2,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-11"},"id":"zai/glm-5","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":26.4603,"average_ttft":null,"average_latency":2.4244,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":26.4603,"average_ttft":null,"average_latency":2.4244,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-5-turbo","base_model_name":"glm-5-turbo","max_context_window":200000,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-02-01"},"id":"zai/glm-5-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":7.9716,"average_ttft":null,"average_latency":5.1879,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":7.9716,"average_ttft":null,"average_latency":5.1879,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text, JSON object, or JSON schema output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-5.1","base_model_name":"glm-5.1","max_context_window":200000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-07"},"id":"zai/glm-5.1","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":9.205,"average_ttft":null,"average_latency":6.9907,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":9.205,"average_ttft":null,"average_latency":6.9907,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","default":1,"range":{"min":0,"max":2},"description":"Controls the randomness of the model. Lower values make the model more deterministic.","required":false},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","default":1,"range":{"min":0,"max":1},"description":"The cumulative probability of the top tokens to keep.","required":false},"frequency_penalty":{"name":"frequency_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for repeating tokens.","required":false},"presence_penalty":{"name":"presence_penalty","type":"number","default":0,"range":{"min":-2,"max":2},"description":"The penalty for tokens that are already in the text.","required":false},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"n":{"name":"n","type":"int","default":1,"description":"The number of completions to generate.","required":false}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":true,"model_name":"zai/glm-5.2","base_model_name":"glm-5.2","max_context_window":1000000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":["display_name","metadata"],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.45503407398358586,"ci_lo":0.42052148157196967,"model":"glm-5-2","config":"mini_swe_agent_glm_5_2_max","n_runs":4,"source":"deep-swe","ci_half":0.01725629620580811,"harness":"mini-swe-agent","version":"v1.1","n_passed":197,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":197,"pass_at_1":0.43777777777777777,"pass_at_4":0.7699115044247787,"pass_rate":0.43777777777777777,"n_attempted":450,"ci_attempted":450,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9199075743111114,"n_tasks_in_set":113,"median_cost_usd":3.4637479200000003,"mean_agent_steps":129.12666666666667,"reasoning_effort":"max","mean_cache_tokens":12344954.453333333,"mean_input_tokens":12606560.215555556,"n_tasks_attempted":113,"mean_output_tokens":78175.30666666667,"median_agent_steps":123,"n_tasks_passed_any":87,"median_input_tokens":11208642,"median_output_tokens":75760,"mean_duration_seconds":2629.2083211311115,"median_duration_seconds":2304.8350069999997,"median_peak_context_tokens":142129,"median_output_tokens_to_pass":75146}},"release_date":"2026-06-13"},"id":"zai/glm-5.2","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":18.7095,"average_ttft":null,"average_latency":3.6665,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":18.7095,"average_ttft":null,"average_latency":3.6665,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-5.3","base_model_name":"zai/glm-5.3","max_context_window":1000000,"input_cost":1.4,"output_cost":4.4,"cache_hit_input_cost":0.26,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.7197652266845449,"ci_lo":0.6593922012533708,"model":"glm-5-3","config":"mini_swe_agent_glm_5_3_max","n_runs":4,"source":"deep-swe","ci_half":0.030186512715587,"harness":"mini-swe-agent","version":"v1.1","n_passed":311,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":311,"pass_at_1":0.6895787139689579,"pass_at_4":0.8761061946902655,"pass_rate":0.6895787139689579,"n_attempted":451,"ci_attempted":451,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":3.9933584893126386,"n_tasks_in_set":113,"median_cost_usd":3.1315945999999992,"mean_agent_steps":124.47228381374723,"reasoning_effort":"max","mean_cache_tokens":13106008.833702883,"mean_input_tokens":13272344.266075388,"n_tasks_attempted":113,"mean_output_tokens":80435.60975609756,"median_agent_steps":114,"n_tasks_passed_any":99,"median_input_tokens":10137783,"median_output_tokens":74953,"mean_duration_seconds":2116.1784804168515,"median_duration_seconds":1842.82226,"median_peak_context_tokens":144729,"median_output_tokens_to_pass":74814}},"release_date":"2026-08-18"},"id":"zai/glm-5.3","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":0,"enforce_function_call":0,"metrics":{"average_tps":11.6368,"average_ttft":null,"average_latency":9.5354,"uptime_percent":100,"cache_hit_percentage":34.4086},"throughput":{"average_tps":11.6368,"average_ttft":null,"average_latency":9.5354,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-5.3-flash","base_model_name":"zai/glm-5.3-flash","max_context_window":1000000,"input_cost":0.15,"output_cost":0.5,"cache_hit_input_cost":0.03,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"benchmarks":{"deepswe":{"ci_hi":0.6777082789455078,"ci_lo":0.590148863911635,"model":"glm-5-3-flash","config":"mini_swe_agent_glm_5_3_flash_max","n_runs":4,"source":"deep-swe","ci_half":0.04377970751693644,"harness":"mini-swe-agent","version":"v1.1","n_passed":284,"ci_method":"95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R))","ci_passed":284,"pass_at_1":0.6339285714285714,"pass_at_4":0.8495575221238938,"pass_rate":0.6339285714285714,"n_attempted":448,"ci_attempted":448,"generated_at":"2026-09-22T06:27:15.860279+00:00","mean_cost_usd":0.48196371245535713,"n_tasks_in_set":113,"median_cost_usd":0.389975125,"mean_agent_steps":122.890625,"reasoning_effort":"max","mean_cache_tokens":11770874.857142856,"mean_input_tokens":12387025.401785715,"n_tasks_attempted":113,"mean_output_tokens":72829.77008928571,"median_agent_steps":110,"n_tasks_passed_any":96,"median_input_tokens":9358476.5,"median_output_tokens":67491,"mean_duration_seconds":1537.7995419129463,"median_duration_seconds":1322.635727,"median_peak_context_tokens":136183.5,"median_output_tokens_to_pass":68067.5}},"release_date":"2026-08-26"},"id":"zai/glm-5.3-flash","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":212.4732,"average_ttft":7.1378,"average_latency":111.7231,"uptime_percent":98.8679,"cache_hit_percentage":66.5202},"throughput":{"average_tps":212.4732,"average_ttft":7.1378,"average_latency":0.1117231,"number_of_requests":null},"benchmark":null},{"project":null,"provider":{"project":null,"provider_name":"Z.ai","provider_id":"zai","extra_kwargs":{},"created_at":"2026-06-06T08:37:06.175659Z","updated_at":"2026-06-06T08:37:06.175665Z","respan_discount_rate":0,"models_sync_config":{},"kind":"host","id":"zai"},"supported_params":{"temperature":{"name":"temperature","type":"number","range":{"max":1,"min":0},"default":1,"required":false,"description":"Z.AI sampling temperature."},"max_tokens":{"name":"max_tokens","type":"int","description":"The maximum number of tokens to generate.","required":false},"top_p":{"name":"top_p","type":"number","range":{"max":1,"min":0.01},"default":0.95,"required":false,"description":"Z.AI nucleus-sampling probability."},"stop":{"name":"stop","type":"string","default":"\n","description":"The stop sequence for the model to stop generation.","required":false},"response_format":{"name":"response_format","type":"object","default":{"type":"text"},"required":false,"description":"Controls text or JSON-object output formatting."}},"affiliation_category":"keywordsai","is_managed":true,"is_called_by_custom_name":false,"model_name":"zai/glm-5v-turbo","base_model_name":"zai/glm-5v-turbo","max_context_window":200000,"input_cost":1.2,"output_cost":4,"cache_hit_input_cost":0.24,"cache_creation_input_cost":0,"respan_discount_rate":null,"overridden_fields":[],"load_balance_backups":[],"status":"active","is_verified":true,"model_type":"chat","metadata":{"release_date":"2026-04-01"},"id":"zai/glm-5v-turbo","is_byok":false,"effective_discount_rate":0,"response_api_support":null,"function_call":1,"image_support":1,"enforce_function_call":0,"metrics":{"average_tps":21.6317,"average_ttft":null,"average_latency":2.7932,"uptime_percent":100,"cache_hit_percentage":0},"throughput":{"average_tps":21.6317,"average_ttft":null,"average_latency":2.7932,"number_of_requests":null},"benchmark":null}],"error":null}