Skip to content

agentix.providers.litellm

litellm

LiteLLM bridge — one adapter, 100+ providers.

LiteLLM <https://docs.litellm.ai/>_ exposes a single OpenAI-shaped acompletion that fans out to OpenAI, Azure, Anthropic, Bedrock, Vertex, Mistral, Groq, Ollama and many more behind provider-prefixed model ids ("gpt-4o", "anthropic/claude-opus-4-8", "gemini/gemini-2.0-flash", "ollama/llama3", …). Install with pip install "agentix[litellm]".

This is the pragmatic "works with whatever the user already has" option; the dedicated adapters (OpenAIModel, GeminiModel, BedrockModel, OllamaModel) exist for when you want first-party control and typed knobs.

LiteLLMModel 

LiteLLMModel(
    *, model: str, client: Any = None, **extra: Any
)

A :class:~agentix.model.ModelFn backed by litellm.acompletion.

model uses LiteLLM's provider-prefixed ids. extra is forwarded to acompletion (e.g. api_base, api_key, temperature, num_retries). For tests, inject client= — any object exposing an async acompletion(**kwargs) (the litellm module itself by default).

with_response_format 

with_response_format(
    schema: dict[str, Any],
) -> LiteLLMModel

Return a copy that requests JSON-schema output (for response_model).