litellm
by BerriAI
LiteLLM is a gateway and Python library that lets you call more than 100 AI model providers, such as OpenAI, Anthropic, Bedrock and Azure, using one OpenAI-style format. It is for teams that want to switch between providers, track spending and control access from one place.
- Stars
- 62.1k +51 a day
- Licence
- MIT
- Runs on
- A small server
- Setup
- Moderate
- Language
- Python
- Age
- 1188 days
What you can do with it
- Call models from OpenAI, Anthropic, Gemini and others through one consistent interface
- Run a central proxy server that issues virtual keys and tracks spend per user or team
- Set up load balancing, fallbacks and guardrails across several AI providers
Make money with it
A freelancer could set up and manage a LiteLLM gateway for small businesses that want one place to control AI access and costs, charging for setup and support.
An idea, not financial advice. Check the licence before charging for anything built on it.
Ways a business could use it
- Cut AI costs by routing requests to cheaper models and tracking spend per customer or project
- Avoid being locked in to one AI provider by switching models without rewriting your code
Can you use it commercially?
Free to use, change and sell (MIT-style terms in the licence file). Some folders may carry other terms.
Not legal advice. Read the project's licence file before building a product on it.
Getting it running
Install the Python SDK with uv or pip, or run the proxy with 'uv tool install litellm[proxy]' and the 'litellm' command, or deploy it with Docker or one-click hosting templates.
Follow the official instructions in the project README.
Things to check
- Licence is listed as unclear (NOASSERTION), and some features are in a paid Enterprise tier
- You need your own paid API keys for the underlying AI providers
- The README is partly cut off, so some features could not be checked
Who's talking about it
- Rost (rosgluk): Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
- Rost Glukhov: Trending Open Source AI Projects on GitHub, October 2026 Featured in a roundup
Checked 27 Oct 2026. Summary drafted by AI from the project's README.