zexadev/gemini-web2api-go

Gemini web → OpenAI-compatible + native Gemini API, self-hosted, no API key. Reverse-proxies gemini.google.com into /v1/chat/completions + /v1beta generateContent: single Go binary, Chrome TLS fingerprint, cookie pool, auto-renewal, proxy pool, admin dashboard, SQLite/MySQL/PG, image & video generation · 把 Gemini 网页反代成 OpenAI 兼容 / Gemini 原生 API

What it solves

This project acts as a bridge that converts the free web interface of Google Gemini into an OpenAI-compatible API. It allows users to integrate Gemini into tools that expect the standard OpenAI API (like Cursor, Dify, or Cherry Studio) without needing a paid Google API key or consuming official Google Cloud quota.

How it works

It functions as a reverse proxy that mimics a real Chrome browser session. It uses TLS fingerprinting to appear as a legitimate browser to Google's servers, bypassing common bot detection. It manages a pool of cookies and proxies to ensure stability and load balancing. When you send a request, the service translates it into the web-based protocol used by gemini.google.com, processes the response, and streams it back to your client in the standard OpenAI format.

Who it’s for

This is for developers and power users who want to use Gemini's models (including Pro and thinking models) in their own applications or local AI tools without paying for the official Google Generative AI API. It is particularly useful for those who want to self-host a reliable, multi-account proxy for their AI workflows.

Highlights

  • OpenAI Compatibility: Exposes standard /v1/chat/completions endpoints for seamless integration with existing AI clients.
  • No API Key Required: Operates by reverse-engineering the web interface, meaning no official Google API key or paid quota is needed.
  • Advanced Features: Supports Gemini's "thinking" models, image/video generation, and web search capabilities via an integrated MCP server.
  • Robust Infrastructure: Features a built-in admin dashboard, SQLite/MySQL/PostgreSQL support, automatic cookie renewal, and proxy pool management to prevent IP bans.

Related

  • Project
    iBUHub/AIStudioToAPI

    AIStudioToAPI is a self‑hosted bridge that turns Google AI Studio’s web UI into OpenAI, Gemini, and Anthropic‑compatible HTTP APIs. It automates a Camoufox browser to log in, supports multiple Google accounts, tool calls, streaming, and offers a web console. Install via npm or Docker, configure with environment variables, and call the familiar `/v1/*` or `/v1beta/*` endpoints to access Gemini’s multimodal models.

  • Project
    Nativu5/Gemini-FastAPI

    An OpenAI-compatible API wrapper for web-based Gemini models that allows free access using session cookies instead of an API key.

  • Project
    zhiyu1998/Gemi2Api-Server

    Gemi2Api‑Server is a FastAPI‑based bridge that lets you call Google Gemini via an OpenAI‑compatible REST API. It authenticates with Gemini using your browser cookies, forwards chat‑completion requests, optionally proxies generated images, and provides a simple admin UI. Deployable locally, via Docker, or on Render/HuggingFace, it’s useful for developers who want Gemini access without a formal public API.

  • Project
    GewoonJaap/gemini-cli-openai

    A Cloudflare Worker that transforms Google's Gemini models into OpenAI-compatible endpoints, allowing Gemini to be used with any OpenAI SDK or client.

  • Project
    Sophomoresty/gemini-web2api

    gemini‑web2api is a Python server that proxies Google Gemini’s private web API and presents it as an OpenAI‑compatible endpoint (`/v1/chat/completions`, `/v1/models`, etc.). It supports optional API‑key auth, streaming, function calling, image input, multiple Gemini model aliases, adjustable reasoning depth, and can run directly or inside Docker.