# songquanpeng/one-api

LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

Repository: https://github.com/songquanpeng/one-api
Canonical: https://ross.abutalabs.com/products/one-api
Homepage: https://oneapi.justsong.cn/
Language: JavaScript
License: MIT
License Family: permissive
Topics: openai-api, proxy, chatgpt, gpt, openai, api, api-gateway, azure-openai-api, claude, ernie-bot, gemini
Last push: 2026-01-09T03:26:43+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 61, release rhythm 28, longevity 87
- inputs: {"age_days": 1229, "days_push": 236, "days_rel": 577, "gap_med": 42, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 36591, forks 6830 (observed 2026-08-28T04:12:01.168991+00:00)

## What it is
One API is a self-hosted LLM API gateway and key management system that unifies OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, and many Chinese LLM providers behind a single OpenAI-compatible API. It ships as a single binary or Docker image with a web UI for token management, quota control, and key redistribution to downstream users.

## Use cases
- unify multiple LLM providers behind one OpenAI-compatible endpoint
- manage and redistribute OpenAI API keys to a team
- set quotas and rate limits per user for LLM access
- self-host an LLM API gateway with Docker
- switch between Claude, Gemini, and GPT without changing client code
- track and bill LLM token usage across users

## When to choose
- you need one unified API endpoint across many LLM providers
- you want to distribute LLM access with per-user keys, quotas, and usage tracking
- you want a lightweight single-binary or Docker deployment with a web admin UI

## When to avoid
- you only use a single LLM provider and don't need key management
- you need enterprise-grade gateway features like advanced observability or SSO
- you cannot self-host and need a fully managed service

## Facets
- artifact type: service
- maturity: stable
- function: api-gateway, proxy, llm-inference, http-server, middleware
- domain: large-language-models, artificial-intelligence, apis, self-hosted, developer-tools
- platform: self-hosted, cross-platform
- tags: openai-api, llm-gateway, key-management, api-redistribution, multi-provider, chatgpt-proxy, docker, linux, web-server

## Member repositories
- songquanpeng/one-api (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.168991+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 2026-08-29T16:26:10.499263+00:00, confidence not recorded.
  - readme: https://github.com/songquanpeng/one-api (fetched 2026-08-28T04:12:01.168991+00:00, sha dd89b128b049)
  - homepage: https://oneapi.justsong.cn/ (fetched 2026-08-29T07:47:51.421136+00:00, sha 039dee48cbc9)
- Data as of 2026-08-30T08:39:29.467469+00:00.