Skip to main content
POST
Create a custom model

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

name
string
required

Display name, unique within the company.

litellm_model
string
required

LiteLLM model string, e.g. 'openai/gpt-4-turbo' or 'azure/my-deployment'.

model_type
string
default:Large Language Model

Model type (e.g. 'Large Language Model', 'Embedding Model').

endpoint
string | null

Custom API base URL (api_base in LiteLLM).

api_key
string | null

API key for the custom model endpoint.

temperature
number<double> | null

Sampling temperature to use for every request to this model. Omit to let each calling feature use its own value. Models that accept only one temperature are set to it regardless of what is submitted here.

Required range: 0 <= x <= 2

Response

id
string<uuid>
required

Unique ID for this custom model.

name
string
required

Display name, unique within the company.

technical_name
string
required

LiteLLM identifier (custom-{uuid}).

litellm_model
string
required

LiteLLM model string, e.g. 'openai/gpt-4-turbo'.

model_type
string
required

Model type.

enabled
boolean
required

Whether the model is active.

is_default
boolean
required

Whether this is the company's default custom model.

endpoint
string | null

Custom API base URL.

temperature
number<double> | null

Sampling temperature sent for every request to this model. Null means no temperature is configured and the calling feature's own value is used.

required_temperature
number<double> | null

The only temperature this model accepts, when it accepts exactly one. Set for models that have removed sampling parameters; null for every other model.

max_temperature
number<double> | null

Highest temperature this model's provider accepts. Null for a model served from its own endpoint, where no provider bound applies.