Library / SDK
Inference & Serving
LiteLLM
1One 2API 3for 4every 5LLM 6provider.
the six Ws · specification
W1
Who
Open-source library and proxy with a paid tier.
W2
What
Call 100+ providers through one OpenAI-style interface.
W3
Where
A Python SDK or a self-hosted proxy.
W4
When
When you must swap or route between providers.
W5
Why
Avoids rewriting code for each new model vendor.
W6
With
Provider API keys and your app or gateway.