
New API
A self-hosted AI gateway that connects many upstream model services and exposes one consistent API, with routing, access control, usage tracking and a web console.
- GitHub stars
- 52k
- Last commit
- yesterday
- Latest release
- v1.0.0-rc.49
- Licence
- AGPL-3.0
- Self-hosted
- Yes

New API is an AI gateway you host yourself, built for apps, agents and teams. It lets you plug in upstream model services, present one consistent API to clients, and handle routing, access, usage and cost management centrally. It is written in Go and released under the AGPL-3.0 license.
It can convert between formats so that various LLMs are reachable through OpenAI-compatible, Claude-compatible or Gemini-compatible interfaces. Supported upstreams range from OpenAI, Anthropic and Gemini to Azure OpenAI, AWS Bedrock, Vertex AI, DeepSeek and Qwen, plus other compatible services, and a web console is used for administration.
Typical uses are sharing authorized model access across a team, switching providers without reconfiguring every client, and operating a private multi-model service. The README stresses lawful, authorized use: users must obtain upstream keys legitimately, follow upstream terms, and meet any regulatory obligations if they offer AI services to the public. It suits teams and organizations that need centralized model management.
Key features
- Unified gateway for multiple upstream model services
- OpenAI, Claude and Gemini compatible formats
- Routing, access control and usage tracking
- Cost accounting and usage analytics
- Web console for administration
- Self-hosted private deployment
Pricing: Free and open source under the AGPL-3.0 license.




























