LiteLLM

Inference & Routing

One API client and proxy for 100+ providers.

What it’s for

LiteLLM translates the OpenAI completion format to every major provider, so switching models is a one-line change instead of a rewrite. Its proxy server adds centralized API keys, budgets, rate limits and spend tracking for your whole team.

How to use it

Use the Python or JS SDK directly with litellm.completion(), or deploy the proxy so all your apps hit one endpoint while LiteLLM handles routing, fallbacks and budget limits per team or project.

Pricing

Open source (MIT). Enterprise proxy features and the managed cloud are paid.

Website ↗ GitHub ↗