< cd ../gallery
[AI & ML]

litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]
BerriAI
@BerriAI
maintainer
★ 53.5k stars
go to website ↗github
litellm — preview
litellm repository preview
# README
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]. Maintained by BerriAI on GitHub, where it has earned 53,514 stars from the community.
It's actively developed around ai-gateway, anthropic, azure-openai, and is a solid reference for anyone building with these tools.
# tags
# install
npm install litellm
languages
Python84.976%
TypeScript12.429%
HTML1.458%
Rust0.373%
Go0.236%
HCL0.21%
Shell0.093%
CSS0.037%
Makefile0.022%
PLpgSQL0.011%
Ruby0.006%
last commit1 week ago
license
more FastAPI repos
$ made-with-fastapi
rssllmmadewithwhat

Ask MadeWithWhat

AI answers may contain mistakes — please double-check important details.