TOOLORA / Local reading edition
LiteLLM
Unify model calls through an SDK or proxy gateway, managing virtual keys, budgets, routing and usage.
Overview
LiteLLM normalizes model services behind one calling format, as a Python SDK or shared AI Gateway. The proxy manages virtual keys, spend, load balancing and guardrails for switching providers or centralizing access. It is not itself a generative model: connected services perform inference. Check licensing and enterprise-feature scope for the deployed version.
- Company country / region
- United States · Company headquarters
Official sources and references
- Official websitehttps://www.litellm.ai/
- Documentationhttps://docs.litellm.ai/
Descriptions summarize public information; consult official websites for features, pricing and regional availability.