Repolode
Submit
iimeta

iimeta/fastapi

Self-hosted gateway that exposes many LLM providers (OpenAI, Claude, Gemini, DeepSeek, Qwen, and more) behind one OpenAI-compatible API.

View on GitHubWebsite
Stars
304
Forks
44
Open issues
0
Last commit
yesterday

What is it?

Fast API is an enterprise-oriented LLM API integration system written in Go. It lets business systems call models from many providers, including OpenAI, Azure, Anthropic Claude, Gemini, DeepSeek, Qwen, Baidu ERNIE, iFlytek Spark, Zhipu GLM, Doubao and Grok, through a single OpenAI-compatible endpoint. Callers integrate once and can switch or add backends without changing their own code.

The project includes a web admin console, a user portal and a reseller portal, so operators can manage channels and accounts from the browser. It can be deployed with Docker, and the README also mentions cluster and multi-region deployment. Demo logins for the community and professional editions are provided.

The main repository is the API service; the web frontend, admin UI and SDK live in separate repositories under the same organization.

Key features

  • 01Single OpenAI-compatible chat completions endpoint for many LLM providers
  • 02Supports streaming requests in the OpenAI request format
  • 03Web admin, user and reseller consoles
  • 04Docker one-command deployment and cluster or multi-region deployment

Use cases

  • Giving an application access to several LLM providers through one API
  • Switching or adding model backends without changing client code
  • Running an internal or resold LLM API service with account and quota management

Quick start

  1. 1

    Deploy with Docker using the guide linked in the README

  2. 2

    Follow the quick start guide on the project website

Things to know

  • The README gives no install command, so setup relies on the external Docker guide.
  • Most of the documentation and the README are in Chinese.

In collections

Claude Code tools, skills & pluginsSelf-hosted appsMicroservice frameworks & service infrastructure

Topics

#llm#api-gateway#openai-compatible#go#self-hosted#docker#multi-model#api#chatgpt#claude

FAQ

What is fastapi?
Self-hosted gateway that exposes many LLM providers (OpenAI, Claude, Gemini, DeepSeek, Qwen, and more) behind one OpenAI-compatible API. Fast API is an enterprise-oriented LLM API integration system written in Go. It lets business systems call models from many providers, including OpenAI, Azure, Anthropic Claude, Gemini, DeepSeek, Qwen, Baidu ERNIE, iFlytek Spark, Zhipu GLM, Doubao and Grok, through a single OpenAI-compatible endpoint. Callers integrate once and can switch or add backends without changing their own code.
Is fastapi free to use? What license does it have?
fastapi is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is fastapi still maintained?
Actively maintained. The last commit to fastapi was on Nov 6, 2026.
What can I use fastapi for?
Giving an application access to several LLM providers through one API Switching or adding model backends without changing client code Running an internal or resold LLM API service with account and quota management
How do I install fastapi?
Deploy with Docker using the guide linked in the README Follow the quick start guide on the project website
Where can I get fastapi?
The source code and installation instructions are on GitHub: https://github.com/iimeta/fastapi

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects