Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

321 B
Raw Blame
python3 -m build
twine upload --verbose dist/litellm-1.18.13.dev4.tar.gz -u __token__ - 


Note: You might need to make a MANIFEST.ini file on root for build process incase it fails 

Place this in MANIFEST.ini
recursive-exclude venv *
recursive-exclude myenv *
recursive-exclude py313_env *
recursive-exclude **/.venv *