LiteLLM
Open-source AI gateway that puts your AI stack behind one OpenAI-compatible key.
LiteLLM is an open-source AI gateway that puts multiple LLM providers, agents, and MCP servers behind a single OpenAI-compatible API and one login. It addresses the operational overhead of managing many model endpoints by centralizing key management, spend visibility, and request routing, so teams can swap models without changing application code.
The gateway provides virtual keys, teams, spend tracking, budgets, rate limits, guardrails, audit logs, and routing, including Auto Routing for model selection. It supports SSO, SCIM, OIDC/JWT auth, secret manager integration with key rotation, org and team admin roles, request/response logging, Prometheus metrics, and LLM fallbacks. Deployment is self-hosted, with air-gapped and multi-region control plane options available.
LiteLLM is aimed at platform teams and organizations running AI workloads in production. It is packaged as a free, self-hosted Open Source edition with community support, and an Enterprise edition priced by annual gateway request capacity, deployment architecture, and support needs, with a 30-day trial available.
12 alternatives to LiteLLM
Ranked by how well each tool replaces LiteLLM: shared features, audience, price and popularity.
Open source LLM gateway that connects AI agents and workflows to any provider.
Covers 11 of 15 key features.
Free planOpen source65 out of 100 match$19/mo- 65 out of 100 match$20/mo
- 64 out of 100 matchUsage-based
- 64 out of 100 matchUsage-based
- 63 out of 100 match—
- 63 out of 100 matchFree
- 63 out of 100 matchFree
Serve and scale open-source and custom AI models on the fastest, most reliable inference
Covers 8 of 15 key features.
Free plan62 out of 100 matchFree- 62 out of 100 matchContact sales
Open-source AI gateway written in Go providing one OpenAI- and Anthropic-compatible API in
Covers 8 of 15 key features.
Free planOpen source62 out of 100 matchContact sales