# fruitbars/simple-one-api

OpenAI 接口接入适配，支持千帆大模型平台、讯飞星火大模型、腾讯混元以及MiniMax、Deep-Seek，等兼容OpenAI接口，仅单可执行文件，配置超级简单，一键部署，开箱即用.  Seamlessly integrate with OpenAI and compatible APIs using a single executable for quick setup and deployment.

Repository: https://github.com/fruitbars/simple-one-api
Canonical: https://ross.abutalabs.com/products/simple-one-api
Language: Go
License: MIT
License Family: permissive
Last push: 2026-08-23T13:38:22+00:00

## Health v2 (maintenance only)
Score: 91/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 59
- inputs: {"age_days": 828, "days_push": 10, "days_rel": 10, "gap_med": 3.0, "n_releases_24m": 5}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2329, forks 204 (observed 2026-08-28T04:06:37.681017+00:00)

## What it is
A single-binary Go gateway that unifies access to multiple LLM providers (Qianfan, iFlytek Spark, Tencent Hunyuan, MiniMax, DeepSeek, etc.) behind OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages protocols. It bundles an embedded web chat UI, a visual configuration admin panel backed by SQLite, usage statistics, and a Wails desktop app.

## Use cases
- expose a unified OpenAI-compatible API for multiple Chinese LLM providers
- load balance requests across several LLM API keys and models
- self-host a gateway so existing OpenAI SDK code can call other model vendors
- run a local web chat interface backed by different LLM providers
- track token usage and latency across LLM providers
- deploy an LLM proxy as a single executable or Docker container
- route chat requests with round-robin, preferred, or hash strategies across providers

## When to choose
- you need one OpenAI-compatible endpoint in front of many LLM vendors, especially Chinese providers
- you want a single-binary or Docker deployment with minimal configuration
- you need built-in admin UI, chat UI, and usage stats without extra services
- you want key rotation, rate limiting, circuit breaking, and model aliasing at the gateway level

## When to avoid
- you need billing, quota accounting, or cost management for upstream providers (explicitly out of scope)
- you need a full LLM ops platform with team management, fine-grained RBAC, or enterprise features like LiteLLM or One API at scale
- you only use OpenAI directly and need no multi-provider adaptation
- you require encrypted-at-rest configuration storage (SQLite is not encrypted)

## Facets
- artifact type: service
- maturity: active
- function: api-gateway, llm-inference, http-server, chatbot, proxy, middleware, self-hosted
- domain: large-language-models, artificial-intelligence, apis, self-hosted, developer-tools, chatbots
- platform: windows, self-hosted, cross-platform, go
- tags: openai-compatible-api, llm-gateway, api-adapter, multi-provider, load-balancing, single-binary, chat-completions, anthropic-messages, embeddings, wails-desktop-app, web-chat-ui, sqlite-config, linux, macos, docker, web-server, desktop

## Member repositories
- fruitbars/simple-one-api (main) score 91

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:37.681017+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 2026-08-30T02:38:10.706179+00:00, confidence not recorded.
  - readme: https://github.com/fruitbars/simple-one-api (fetched 2026-08-28T04:06:37.681017+00:00, sha a0d239824f4d)
- Data as of 2026-08-30T08:39:29.467469+00:00.