# 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.

Repository: https://github.com/QuantumNous/new-api
Canonical: https://ross.abutalabs.com/products/new-api
Homepage: https://www.newapi.ai
Language: Go
License: AGPL-3.0
License Family: copyleft
Topics: claude, gemini, openai, rerank, ai-gateway, deepseek, newapi
Last push: 2026-08-26T13:07:25+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 73
- inputs: {"age_days": 1027, "days_push": 7, "days_rel": 7, "gap_med": 0, "n_releases_24m": 472}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 46459, forks 11026 (observed 2026-08-28T04:12:11.076645+00:00)

## What it is
New API is a self-hosted LLM gateway and AI asset management system that aggregates 30+ model providers behind a single unified endpoint. It cross-converts provider APIs into OpenAI-, Claude-, and Gemini-compatible formats while adding routing, authentication, usage analytics, and cost control.

## Use cases
- expose all my LLM providers through one OpenAI-compatible endpoint
- self-host an AI gateway to manage API keys and quotas for a team
- convert Claude and Gemini models to OpenAI API format
- track token usage and costs across multiple AI providers
- load balance and failover between LLM providers
- resell or distribute model access with per-user keys and billing
- use one API base URL with tools like LangChain, Dify, or Open WebUI

## When to choose
- you need a unified endpoint across many LLM providers
- you want self-hosted key management, quotas, and usage analytics
- you need protocol conversion between OpenAI, Claude, and Gemini formats
- you run a team or platform that shares model access with cost control

## When to avoid
- you only call a single provider directly with no need for aggregation
- you need a fully managed cloud gateway with no self-hosting overhead
- your usage may conflict with upstream provider terms of service

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, middleware, auth, analytics, rate-limiting, http-server
- domain: large-language-models, artificial-intelligence, apis, self-hosted, developer-tools
- platform: self-hosted, go
- tags: llm-gateway, openai-compatible, api-proxy, model-aggregation, cost-tracking, channel-management, claude, gemini, docker, linux, web-server

## Member repositories
- QuantumNous/new-api (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:11.076645+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:21:36.805226+00:00, confidence not recorded.
  - readme: https://github.com/QuantumNous/new-api (fetched 2026-08-28T04:12:11.076645+00:00, sha c61a33c88b1e)
  - homepage: https://www.newapi.ai (fetched 2026-08-29T07:45:08.335213+00:00, sha 31bcf48a332e)
  - site_page: https://docs.newapi.ai (fetched 2026-08-29T07:45:08.344748+00:00, sha 0ce40820e008)
- Data as of 2026-08-30T08:39:29.467469+00:00.