iBUHub/AIStudioToAPI

A wrapper that exposes Google AI Studio Build as OpenAI, Gemini, and Anthropic compatible APIs.（一个将 Google AI Studio Build 封装为兼容 OpenAI / Gemini / Anthropic 风格 API 的工具）

What it solves

This project provides a way to access Google AI Studio's "Build App" web interface as if it were a standard API. It solves the problem of wanting to use Gemini models (including image generation and TTS) via programmatic interfaces while leveraging the web-based AI Studio environment, effectively turning a browser-based tool into a compatible API backend.

How it works

The tool acts as a proxy server that uses browser automation (via the Camoufox browser) to interact with the AI Studio web interface. It translates incoming API requests into browser actions and then translates the web responses back into API formats. It supports multiple Google accounts and can automatically switch between them to manage limits or failures.

Who it’s for

Developers who want to integrate Gemini models into their own applications or existing AI clients (like AMC WebUI) but prefer or need to use the AI Studio web interface instead of a direct API key, or those who need to manage multiple accounts for higher throughput.

Highlights

  • Multi-API Compatibility: Supports OpenAI, Gemini, and Anthropic API formats.
  • Tool Use Support: Enables Function Calling across all supported API interfaces.
  • Account Management: Supports multiple Google accounts with automatic switching and a VNC-based login system for Docker deployments.
  • Flexible Model Control: Allows forcing thinking mode, web search, and code execution via model name suffixes.
  • Proxy Support: Includes account-specific proxy mapping to handle network restrictions.

Related

  • Project
    zexadev/gemini-web2api-go

    A self-hosted proxy that turns the free Gemini web app into an OpenAI-compatible API, bypassing the need for API keys and paid quotas.

  • Project
    foxhui/WebAI2API

    A tool that converts web-based AI services into OpenAI-compatible APIs by simulating human browser interactions to bypass bot detection.

  • 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
    justlovemaki/AIClient2API

    AIClient2API is a Node.js‑based proxy that converts client‑only LLM services (Gemini, Claude, Grok, Codex, etc.) into a standard OpenAI‑compatible REST API. It uses adapters to translate requests/responses, supports multi‑account pooling, TLS fingerprint spoofing, and provides a web console, full logging, and agent‑friendly skill files. Run via Docker, configure providers in `configs/provider_pools.json`, and point any OpenAI‑compatible tool to the proxy URL.

  • 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.