Gemini-OpenAI-Proxy

 Gemini-OpenAI-Proxy 这个工具可以起一个服务，将 OpenAI 的 API 调用转为 Gemini Pro API 的 API 调用，从而可以使用现有的 ChatGPT 客户端，体验 Gemini Pro。

OpenAI to Google Gemini https://gemini-openai-proxy.deno.dev

gemini-openai-proxy.zuisong.workers.dev

Gemini-OpenAI-Proxy is a proxy software. It is designed to convert OpenAI API protocol calls into Google Gemini Pro protocol, so that software using OpenAI protocol can use Gemini Pro model without perception.

If you're interested in using Google Gemini but don't want to modify your software, Gemini-OpenAI-Proxy is a great option. It allows you to easily integrate the powerful features of Google Gemini without having to do any complex development work.

Demo

Get api key from https://makersuite.google.com/app/apikey

✅ Gemini Pro

curl -s http://localhost:8000/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "gpt-3.5-turbo",
      "messages": [{"role": "user", "content": "Hello, Who are you?"}],
      "temperature": 0.7
      }'

✅ Gemini Pro Vision

Plan

• /v1/chat/completions
  • stream
  • complete

Model Mappings

OpenAI Model	Gemini Model
gpt-3.5-turbo	gemini-1.0-pro-latest
gpt-4	gemini-1.5-pro-latest
gpt-4-vision-preview	gemini-1.0-pro-vision-latest
gpt-4-turbo	gemini-1.5-pro-latest
gpt-4o	gemini-1.5-flash-latest
gpt-4-turbo-preview	gemini-1.5-pro-latest
...others	gemini-1.0-pro-latest

Run On Serverless:

Cloudflare Workers

build command npm run build:cf_worker

Copy main_cloudflare-workers.mjs to cloudflare-workers

Deno Deploy

build command npm run build:deno

Copy main_deno.mjs to deno deploy

Vercel

build command npm run build:cf_worker

• Alternatively can be deployed with cli: vercel deploy
• Serve locally: vercel dev
• Vercel Functions limitations (with Edge runtime)

Run On Local

deno:

deno task start:deno

node:

npm install && npm run start:node

bun:

bun run start:bun

from https://github.com/zuisong/gemini-openai-proxy