← back to the directory
Library / SDK Inference & Serving

LiteLLM

1One 2API 3for 4every 5LLM 6provider.

the six Ws · specification

W1 Who

Open-source library and proxy with a paid tier.

W2 What

Call 100+ providers through one OpenAI-style interface.

W3 Where

A Python SDK or a self-hosted proxy.

W4 When

When you must swap or route between providers.

W5 Why

Avoids rewriting code for each new model vendor.

W6 With

Provider API keys and your app or gateway.

PythonProxyGateway

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.