Llm Models Models List List

GET

https://api.respan.ai/llm_models/models/list/

GET

/llm_models/models/list/

$ curl https://api.respan.ai/llm_models/models/list/ \
>      -H "Authorization: Bearer <token>"

200Retrieved

1 {
2   "count": 25,
3   "results": [
4     {
5       "provider": {
6         "provider_name": "string",
7         "provider_id": "string",
8         "created_at": "2024-01-15T09:30:00Z",
9         "updated_at": "2024-01-15T09:30:00Z",
10         "id": "string",
11         "project": "string",
12         "respan_discount_rate": 1.1
13       },
14       "supported_params": "string",
15       "model_name": "string",
16       "id": "string",
17       "is_byok": true,
18       "effective_discount_rate": 1.1,
19       "project": "string",
20       "affiliation_category": "custom",
21       "is_managed": true,
22       "is_called_by_custom_name": true,
23       "base_model_name": "string",
24       "display_name": "string",
25       "max_context_window": 1,
26       "input_cost": 1.1,
27       "output_cost": 1.1,
28       "cache_hit_input_cost": 1.1,
29       "cache_creation_input_cost": 1.1,
30       "respan_discount_rate": 1.1,
31       "streaming_support": 1,
32       "function_call": 1,
33       "image_support": 1,
34       "overridden_fields": [
35         "string"
36       ],
37       "status": "active",
38       "is_verified": true,
39       "source": "hardcoded",
40       "model_type": "chat",
41       "metadata": {
42         "privacy_policy_url": "string",
43         "zero_data_retention": true,
44         "prompt_training": true,
45         "prompt_logging": true,
46         "moderation": true,
47         "is_available_on_credits": true,
48         "stream_cancellation_supported": true,
49         "precision": "string",
50         "quantization": "string",
51         "release_date": "string",
52         "context_size": 1,
53         "weekly_tokens": 1,
54         "daily_tokens": 1,
55         "benchmarks": {
56           "deepswe": {
57             "version": "string",
58             "generated_at": "string",
59             "n_tasks_in_set": 1,
60             "model": "string",
61             "harness": "string",
62             "reasoning_effort": "string",
63             "config": "string",
64             "source": "string",
65             "pass_rate": 0.5,
66             "pass_at_1": 0.5,
67             "pass_at_4": 0.5
68           }
69         }
70       }
71     }
72   ],
73   "next": "string",
74   "previous": "string",
75   "total_count": 100,
76   "current_filters": {},
77   "filters_data": {}
78 }

GET/POST /api/models/list/ (Public API) GET/POST /api/llm_models/models/list/ (Platform)

List models. Authentication is optional (OpenRouter-style catalog) — the SAME endpoint serves both public and authenticated callers:

Unauthenticated → managed/shared models only (organization=None). Rate-limited per client IP.
API key / JWT → managed models PLUS the caller’s own custom models.

Read-only: there is no create/write path (ListAPIView); post() only delegates to get() to support POST-body filtering (BE conventions). Both auth modes fully support filtering.

Optionally enriches each model with cross-org performance metrics (opt-in via is_including_metrics) over an absolute UTC [start_time, end_time) window read at time_tick grain (dashboard convention). Each model gets a metrics object: average_tps / average_ttft / average_latency (OpenRouter-style averages), uptime_percent, number_of_requests, cost, the prompt/completion/ cache token sums, and cache_hit_percentage. Sourced from the cross-org get_public_breakdown_metrics reader (clickhouse/tasks.py). The metrics are cross-org aggregates, so they’re identical regardless of auth.

Filtering: Use standard filter syntax: { “filters”: { “affiliation_category”: { “value”: [“CUSTOM”] } } } See boilerplates/keywordsai/feature_docs/shared/filters_api_reference.md

GET/POST /api/models/list/ (Public API) GET/POST /api/llm_models/models/list/ (Platform) List models. **Authentication is optional** (OpenRouter-style catalog) — the SAME endpoint serves both public and authenticated callers: - **Unauthenticated** → managed/shared models only (``organization=None``). Rate-limited per client IP. - **API key / JWT** → managed models PLUS the caller's own custom models. Read-only: there is no create/write path (``ListAPIView``); ``post()`` only delegates to ``get()`` to support POST-body filtering (BE conventions). Both auth modes fully support filtering. Optionally enriches each model with cross-org performance metrics (opt-in via ``is_including_metrics``) over an absolute UTC ``[start_time, end_time)`` window read at ``time_tick`` grain (dashboard convention). Each model gets a ``metrics`` object: average_tps / average_ttft / average_latency (OpenRouter-style averages), uptime_percent, number_of_requests, cost, the prompt/completion/ cache token sums, and cache_hit_percentage. Sourced from the cross-org ``get_public_breakdown_metrics`` reader (clickhouse/tasks.py). The metrics are cross-org aggregates, so they're identical regardless of auth. Filtering: Use standard filter syntax: { "filters": { "affiliation_category": { "value": ["CUSTOM"] } } } See boilerplates/keywordsai/feature_docs/shared/filters_api_reference.md

Authentication

AuthorizationBearer

JWT access token or Respan API key

Query parameters

pageintegerOptional

A page number within the paginated result set.

page_sizeintegerOptional

Number of results to return per page.

Response

countinteger

resultslist of objects

nextstring or nullformat: "uri"

previousstring or nullformat: "uri"

total_countinteger

current_filtersobject

Pydantic model for FilterParamDict. A dictionary that maps metric names to their filter parameters.

Each key is a metric name (str), and each value can be:

A single MetricFilterParamPydantic (one condition)
A List[MetricFilterParamPydantic] (multiple conditions for same metric)
A FilterBundlePydantic (nested filter bundle with connector)

Note: Uses extra=“allow” for dynamic metric name fields. The pydantic_extra annotation tells Pydantic what types to expect for extra fields, and generates typed additionalProperties in JSON Schema.

filters_dataobject