LLM gateways and routers
LiteLLM
Open-source Python SDK and self-hosted proxy server that lets applications call many LLM providers through one OpenAI-compatible API. Teams run the proxy as a shared gateway with virtual keys, budgets, spend tracking, routing, fallbacks and guardrails.
- Pricing model
- Free tier and paid plans
- Free tier
- Yes
- Self-hostable
- Yes
- Open source
- Yes (MIT)
LiteLLM pricing
See LiteLLM's pricing → (opens in a new tab)LiteLLM works with 15 of the LLM providers we track
Each is documented in LiteLLM's own docs, shown with its lowest current rate from the prices we track, per 1M input tokens. LiteLLM may support providers we don't track; its documentation (opens in a new tab) has the full list.
