Update a custom model
Update a custom ML model’s name or temperature, or promote it to the company default. Everything else is fixed at creation: the litellm_model, the model type, the endpoint, and the API key cannot be changed, because the credential is write-only in the gateway and cannot be rewritten without first being read back. Register a new model to change any of them. A model whose provider accepts exactly one temperature keeps that one whatever is submitted. Requires company admin role.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
Body
Display name, unique within the company.
Set to true to mark this as the company's default custom model.
Sampling temperature to use for every request to this model. A model that accepts only one temperature keeps that one whatever is submitted here.
0 <= x <= 2Response
Unique ID for this custom model.
Display name, unique within the company.
LiteLLM identifier (custom-{uuid}).
LiteLLM model string, e.g. 'openai/gpt-4-turbo'.
Model type.
Whether the model is active.
Whether this is the company's default custom model.
Custom API base URL.
Sampling temperature sent for every request to this model. Null means no temperature is configured and the calling feature's own value is used.
The only temperature this model accepts, when it accepts exactly one. Set for models that have removed sampling parameters; null for every other model.
Highest temperature this model's provider accepts. Null for a model served from its own endpoint, where no provider bound applies.