Litelm strips LiteLLM down to 2,900 lines and 2 dependencies
Litelm: LiteLLM Without the Bloat
Litelm is a lean alternative to LiteLLM that keeps only the core call path—model routing, message translation, streaming, tool use, and embeddings—while dropping the proxy server, caching, cost tracking, and dozens of other features. It spans roughly 2,900 lines with just two dependencies (openai and httpx), routes to 19 providers, and mirrors LiteLLM's API so switching is a simple import swap. The project is in alpha with 262 passing tests.
litellm's routing + translation in ~2,900 lines and 2 dependencies (openai, httpx).
- Centigonal
This is a cool project, and the idea of using LLMs to selectively extract features from open source projects is an interesting concept.
The only thing I take issue with is the phrase "LiteLLM Without the Bloat." A lot of the features that have been removed (like cost tracking, streaming, caching) are... kind of the core value proposition of LiteLLM for many of their users.
- khalic
I strongly recommend the authors rewrite the readme by hand. It’s kind of a snif test for how much care someone put into this project.
- clickety_clack
One of the 2 dependencies, httpx, isn't really maintained anymore. Pydantic picked it up as httpx2: https://pydantic.dev/docs/httpx2
- 9dev
Funny, everything you pruned away is the reason I’m deploying LiteLLM in our platform. Having a reliable way to track token spend per customer across different services is important to us, and LiteLLM handles this well
- dlojudice
It would be great if there were a plugin/extension infrastructure. For example, to write the cache and costs however and whenever I see fit