Find tools › Open-source projects › Connect AI to your apps

litellm

Open-source project · by BerriAI

A tool that lets one program talk to many different AI companies in the same way.

For developersVery popular98,646,196 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Call OpenAI, Anthropic and Gemini models with the same code
  • Run one shared AI server for your whole team
  • Switch an app to a cheaper model without rewriting it

How to start

  1. Install the uv Python installer if you do not have it.

  2. In a terminal, run uv tool install 'litellm[proxy]'.

  3. Start the proxy with the model you want, as the README shows, and point your apps at it.

  4. Check the license before relying on enterprise features, which are not all open source.

Good to know. Aimed at developers and ops teams, not end users. Most of the code is open source, but some features are under a separate LiteLLM commercial/enterprise license (GitHub shows the license as NOASSERTION), so check which features you need before relying on them.

Before you install

  • Checked by a personWe read what it does before listing it.
  • Last updated 2026-11-18

More detail

LiteLLM is a Python library and a self-hosted proxy server that lets you call 100+ AI model providers (OpenAI, Anthropic, Gemini, Bedrock, Azure and others) through one OpenAI-style interface.

It removes the need to learn a different SDK and request format for every provider, and the proxy adds team features such as virtual API keys, spend tracking, load balancing and guardrails. Developers and platform teams use it when an app or an organisation needs to switch between or share many models.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map