BigHugger
GH Repository · QuantumNous

new-api

A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management.

stars
48,130
30-day movement
+369123/day
Related entries
60
Connections
3
godockerGomakedeepseeknewapirerankopenaiothergeminiai-gatewayclaude

new-api is a self-hosted AI model gateway that aggregates multiple LLM providers behind a single endpoint. It cross-converts requests into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats and supports rerank endpoints.

Use it when you need one centralized hub to manage, proxy, and normalize access to many models from different providers.

Use it to

  • Aggregate multiple LLM providers behind one API endpoint
  • Expose models in OpenAI, Claude, or Gemini compatible formats
  • Manage model access for a team or enterprise centrally
  • Deploy with Docker as a self-hosted gateway
  • Add rerank endpoints alongside chat models

For Developers and teams managing multiple LLM providers

Role
other
Language
Go
Licence
AGPL-3.0
Forks
11,531
Open issues
726
Last push
2026-09-15
Latest release
v0.0.4 · 2023-12-05
topicsai-gatewayllmopenaiclaudegeminirerank