Llm Models Custom Providers List

Create and list custom LLM providers for an organization Supports both internal (JWT) and public (API key) authentication. - Internal API: Returns all fields - Public API: Hides internal fields (litellm_provider_id, is_managed, moderation) Superadmin access: Superadmins can access ALL custom providers across all organizations. Regular users can only access their own organization's providers. Endpoint: GET/POST /llm_models/custom_providers/ GET/POST /api/llm-models/custom-providers/ Args (POST): - provider_id (Required): Unique identifier for the custom provider - provider_name (Required): Human-readable name for the provider - litellm_provider_id (Optional): Base provider ID for LiteLLM compatibility (e.g., "openai", "anthropic") - moderation (Optional): Moderation setting ("filtered", "unfiltered") - extra_kwargs (Optional): Additional provider-specific configuration (all credentials live here) * api_key: Provider API key * base_url: Custom base URL for the provider's API * temperature: Default temperature setting * max_tokens: Default max tokens setting * timeout: Request timeout in seconds Returns (POST): { "id": 123, "provider_id": "my-custom-openai", "provider_name": "My Custom OpenAI Provider", "litellm_provider_id": "openai", "moderation": "filtered", "extra_kwargs": { "api_key": "sk-custom-key-123", "base_url": "https://api.my-custom-provider.com/v1", "temperature": 0.7, "max_tokens": 4096 }, "organization": 456, "created_at": "2024-01-15T10:30:00Z" } Returns (GET): [ { "id": 123, "provider_id": "my-custom-openai", "provider_name": "My Custom OpenAI Provider", "litellm_provider_id": "openai", ... } ]

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