LiteLLM
Provides a single API gateway to access 140+ LLM providers and 1,800+ models, with spend tracking, budget caps, routing, and governance.
LiteLLM is an AI gateway that provides a single API key to access over 140 LLM providers and 1,800+ models, solving the problem of managing multiple AI endpoints and controlling spend. It is designed for platform teams, developers, and IT/ops in companies of all sizes, especially those needing self-hosted or air-gapped deployments. The gateway offers unified access, spend tracking, budget caps, routing, and governance features, and can be self-hosted or used as a managed service.
Key features
- Single API for 140+ providers
- Access 1,800+ models
- Spend tracking by key/team
- Budget caps and rate limits
- Model routing and swapping
- SSO and team-based access
- Self-hosted and air-gapped
- Day-zero model support
- MCP and agent support
- Observability integrations
- LinkedIn1.6/day
- X0.9/day
GTM channels
- Blog
- Community
- API
- Docs
- Changelog
ICP
- Engineering teams
- DevOps sre teams
- IT teams