From f5b11b72a6dcc8f4e7a16f00a61bdd124cc171d2 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Mon, 8 Jun 2026 22:03:35 +0530 Subject: [PATCH] feat(proxy): publish /v2/model/info in Swagger OpenAPI spec (#29900) * feat(proxy): publish /v2/model/info in Swagger OpenAPI spec Expose the v2 model info endpoint in /docs by removing include_in_schema=False and documenting query parameters used by the admin UI and proxy CLI consumers. Co-authored-by: Cursor * chore(ui): regenerate schema.d.ts for /v2/model/info OpenAPI docs Co-authored-by: Cursor --------- Co-authored-by: Cursor --- litellm/proxy/proxy_server.py | 46 ++++++++++++++- .../proxy_server/test_routes_model_info.py | 9 +++ ui/litellm-dashboard/src/lib/http/schema.d.ts | 56 ++++++++++++++++--- 3 files changed, 101 insertions(+), 10 deletions(-) diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py index 2c21e19dce..213f682b8f 100644 --- a/litellm/proxy/proxy_server.py +++ b/litellm/proxy/proxy_server.py @@ -11742,10 +11742,8 @@ async def _find_model_by_id( @router.get( "/v2/model/info", - description="v2 - returns models available to the user based on their API key permissions. Shows model info from config.yaml (except api key and api base). Filter to just user-added models with ?user_models_only=true", tags=["model management"], dependencies=[Depends(user_api_key_auth)], - include_in_schema=False, ) async def model_info_v2( user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth), @@ -11781,7 +11779,49 @@ async def model_info_v2( ), ): """ - BETA ENDPOINT. Might change unexpectedly. Use `/v1/model/info` for now. + Paginated model metadata for proxy deployments (pricing, provider, team access). + + Returns configured router deployments with enriched `model_info` (costs, provider, + context window, etc.). Sensitive fields such as API keys and api_base are omitted. + + Query parameters: + model: Filter to a single public `model_name`. + user_models_only: When true, only return models created by the calling user. + include_team_models: When true, populate `access_via_team_ids` and `direct_access` + on each model and filter to deployments the caller can use. + page / size: Pagination controls (defaults: page=1, size=50). + search: Case-insensitive partial match on model name or team public name. + modelId: Return a single deployment by LiteLLM model id. + teamId: Filter to models with direct access or team membership for this team id. + sortBy / sortOrder: Sort by model_name, created_at, updated_at, costs, or status. + + Example request: + ``` + curl -X GET 'http://localhost:4000/v2/model/info?include_team_models=true&page=1&size=50' \\ + --header 'Authorization: Bearer sk-1234' + ``` + + Example response: + ```json + { + "data": [ + { + "model_name": "gpt-4", + "litellm_params": {"model": "openai/gpt-4.1"}, + "model_info": { + "id": "abc123", + "litellm_provider": "openai", + "access_via_team_ids": ["team-1"], + "direct_access": true + } + } + ], + "total_count": 1, + "current_page": 1, + "total_pages": 1, + "size": 50 + } + ``` """ global llm_model_list, general_settings, user_config_file_path, proxy_config, llm_router diff --git a/tests/test_litellm/proxy/proxy_server/test_routes_model_info.py b/tests/test_litellm/proxy/proxy_server/test_routes_model_info.py index 9825982437..017f4bd436 100644 --- a/tests/test_litellm/proxy/proxy_server/test_routes_model_info.py +++ b/tests/test_litellm/proxy/proxy_server/test_routes_model_info.py @@ -60,6 +60,15 @@ def test_v2_model_info_invalid_page_returns_422(client, auth_as, empty_router): assert "detail" in response.json() +def test_v2_model_info_in_openapi_schema(): + """``GET /v2/model/info`` is published in the proxy OpenAPI/Swagger spec.""" + from litellm.proxy.proxy_server import get_openapi_schema + + schema = get_openapi_schema() + assert "/v2/model/info" in schema["paths"] + assert "get" in schema["paths"]["/v2/model/info"] + + # --------------------------------------------------------------------------- # GET /v1/model/info, GET /model/info # --------------------------------------------------------------------------- diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index c8ec9d3c72..75a14e0985 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -18441,7 +18441,49 @@ export interface paths { }; /** * Model Info V2 - * @description v2 - returns models available to the user based on their API key permissions. Shows model info from config.yaml (except api key and api base). Filter to just user-added models with ?user_models_only=true + * @description Paginated model metadata for proxy deployments (pricing, provider, team access). + * + * Returns configured router deployments with enriched `model_info` (costs, provider, + * context window, etc.). Sensitive fields such as API keys and api_base are omitted. + * + * Query parameters: + * model: Filter to a single public `model_name`. + * user_models_only: When true, only return models created by the calling user. + * include_team_models: When true, populate `access_via_team_ids` and `direct_access` + * on each model and filter to deployments the caller can use. + * page / size: Pagination controls (defaults: page=1, size=50). + * search: Case-insensitive partial match on model name or team public name. + * modelId: Return a single deployment by LiteLLM model id. + * teamId: Filter to models with direct access or team membership for this team id. + * sortBy / sortOrder: Sort by model_name, created_at, updated_at, costs, or status. + * + * Example request: + * ``` + * curl -X GET 'http://localhost:4000/v2/model/info?include_team_models=true&page=1&size=50' \ + * --header 'Authorization: Bearer sk-1234' + * ``` + * + * Example response: + * ```json + * { + * "data": [ + * { + * "model_name": "gpt-4", + * "litellm_params": {"model": "openai/gpt-4.1"}, + * "model_info": { + * "id": "abc123", + * "litellm_provider": "openai", + * "access_via_team_ids": ["team-1"], + * "direct_access": true + * } + * } + * ], + * "total_count": 1, + * "current_page": 1, + * "total_pages": 1, + * "size": 50 + * } + * ``` */ get: operations["model_info_v2_v2_model_info_get"]; put?: never; @@ -43119,13 +43161,13 @@ export interface operations { /** * @description Unified rate-limit error. * - * Every rate-limit condition surfaced by litellm — whether it originated from - * an upstream LLM provider, a vendor batch endpoint, or one of litellm's own - * proxy-side limiters (parallel-requests, dynamic-rate, batch-rate, budget, - * max-iterations, etc.) — is raised as an instance of this class. + * Every rate-limit condition surfaced by litellm — whether it originated from + * an upstream LLM provider, a vendor batch endpoint, or one of litellm's own + * proxy-side limiters (parallel-requests, dynamic-rate, batch-rate, budget, + * max-iterations, etc.) — is raised as an instance of this class. * - * The :attr:`category` attribute lets callers distinguish the source. See - * :class:`RateLimitErrorCategory` for the available values. + * The :attr:`category` attribute lets callers distinguish the source. See + * :class:`RateLimitErrorCategory` for the available values. */ 429: { headers: {