Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
api_key | str | None | None | API key for the model provider. If None, LiteLLM will try to get it from environment variables. |
api_base | str | None | None | Base URL for the model provider. Use this for custom endpoints or self-hosted models. |
openai_client | AsyncOpenAI | None | None | Pre-configured OpenAI client. If provided, other parameters are ignored. |
http_client | AsyncHTTPClient | None | None | Custom HTTP client to use. |
Functions
__init__
Initialize a LiteLLM provider.
Parameters:
api_key(str | None): API key for the model provider. If None, LiteLLM will try to get it from environment variables.api_base(str | None): Base URL for the model provider. Use this for custom endpoints or self-hosted models.openai_client(AsyncOpenAI | None): Pre-configured OpenAI client. If provided, other parameters are ignored.http_client(AsyncHTTPClient | None): Custom HTTP client to use.
name
Get the provider name.
Returns:
str: The provider name (‘litellm’)
base_url
Get the base URL for the provider API.
Returns:
str: The base URL for the provider API
client
Get the client for the provider.
Returns:
AsyncOpenAI: The LiteLLM client
model_profile
Get the model profile for the named model, if available.
Parameters:
model_name(str): The name of the model
ModelProfile | None: The model profile for the named model, if available