Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed. { "mcpServers" : { "respan-docs" : { "url" : "https://docs.respan.ai/mcp" } } }
This integration supports the Respan gateway and callback logging .
What is LiteLLM? LiteLLM provides a unified Python interface for calling 100+ LLM providers using the OpenAI format. With Respan, you can either:
Gateway — route requests through Respan for observability, fallbacks, and load balancingLogging — keep calling providers directly and export logs to Respan via a callback
Quickstart Install packages pip install litellm respan-exporter-litellm
Gateway mode Route LiteLLM requests through the Respan gateway. This gives you full access to Respan features like fallbacks, load balancing, and prompt management.
import litellm response = litellm.completion( api_key = "YOUR_RESPAN_API_KEY" , api_base = "https://api.respan.ai/api" , model = "gpt-4o-mini" , messages = [{ "role" : "user" , "content" : "Hello!" }], ) print (response.choices[ 0 ].message.content)
Logging mode Register the Respan callback to log all completions automatically. Requests go directly to providers — only the logs are sent to Respan.
import litellm from respan_exporter_litellm import RespanLiteLLMCallback litellm.callbacks = [RespanLiteLLMCallback()] response = litellm.completion( model = "gpt-4o-mini" , messages = [{ "role" : "user" , "content" : "Hello!" }], ) print (response.choices[ 0 ].message.content)
Supported parameters Gateway mode (extra_body) Pass Respan parameters using extra_body when routing through the gateway.
response = litellm.completion( api_key = "YOUR_RESPAN_API_KEY" , api_base = "https://api.respan.ai/api" , model = "gpt-4o-mini" , messages = [{ "role" : "user" , "content" : "Hello!" }], extra_body = { "customer_identifier" : "user-123" , "metadata" : { "session_id" : "abc123" }, "thread_identifier" : "conversation_456" , }, )
Pass Respan parameters inside metadata.respan_params.
response = litellm.completion( model = "gpt-4o-mini" , messages = [{ "role" : "user" , "content" : "Hello!" }], metadata = { "respan_params" : { "workflow_name" : "simple_logging" , "span_name" : "single_log" , "customer_identifier" : "user-123" , } }, )
Configuration Parameter Type Default Description api_keystrRESPAN_API_KEY env varRespan API key. base_urlstr | NoneNoneAPI base URL.
See the LiteLLM Exporter SDK reference for the full API.
Async usage The callback supports async completions automatically:
import litellm from respan_exporter_litellm import RespanLiteLLMCallback litellm.callbacks = [RespanLiteLLMCallback()] response = await litellm.acompletion( model = "gpt-4o-mini" , messages = [{ "role" : "user" , "content" : "Tell me a joke" }], )
Multiple providers LiteLLM’s unified interface means all providers are logged with the same callback:
import litellm from respan_exporter_litellm import RespanLiteLLMCallback litellm.callbacks = [RespanLiteLLMCallback()] # OpenAI litellm.completion( model = "gpt-4o-mini" , messages = [ ... ]) # Anthropic litellm.completion( model = "claude-sonnet-4-5-20250929" , messages = [ ... ]) # Together litellm.completion( model = "together_ai/meta-llama/Llama-3-70b" , messages = [ ... ])
Next Steps 
