0. 背景

使用 Google Gemini 实现 Openai 的兼容 API，可以节省真正的 Openai API Key 的花销。

1. 申请 Google Gemini API key

访问https://ai.google.dev/ 申请。

2. (Optional)Google Gemini 模型说明

3. gemini-openai-proxy Github 地址

https://github.com/zhu327/gemini-openai-proxy

4. 本地部署 gemini-openai-proxy

docker run --restart=always -it -d -p 8080:8080 --name gemini zhu327/gemini-openai-proxy:latest

5. 测试

curl http://localhost:8080/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $YOUR_GOOGLE_AI_STUDIO_API_KEY" \
 -d '{
     "model": "gpt-3.5-turbo",
     "messages": [{"role": "user", "content": "Say this is a test!"}],
     "temperature": 0.7
 }'

示例输出，

{
  "id": "chatcmpl-bc77a209753242bf94a5f83cc7b59c98",
  "object": "chat.completion",
  "created": 1704624098,
  "model": "gemini-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "This is a test!"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0
  },
  "system_fingerprint": ""
}

完结！