OpenAI Chat Completions

OpenAI 兼容对话接口，适合普通文本对话、多轮上下文、图片理解、流式输出和函数调用。

接口信息

项目	值
方法	POST
路径	/v1/chat/completions
完整地址	https://api.gemai.cc/v1/chat/completions
鉴权	Authorization: Bearer sk-你的令牌
Content-Type	application/json

请求体示例

{
  "model": "[官逆]gemini-2.5-pro",
  "messages": [
    {
      "role": "system",
      "content": "你是一个有帮助的助手。"
    },
    {
      "role": "user",
      "content": "你能做什么？"
    }
  ]
}

代码示例

cURL

curl --location 'https://api.gemai.cc/v1/chat/completions' \
  --header "Authorization: Bearer $GEMAI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "[官逆]gemini-2.5-pro",
    "messages": [
      { "role": "user", "content": "你好，请介绍一下你自己。" }
    ]
  }'

JavaScript

const response = await fetch('https://api.gemai.cc/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.GEMAI_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: '[官逆]gemini-2.5-pro',
    messages: [
      { role: 'user', content: '你好，请介绍一下你自己。' },
    ],
  }),
})

const data = await response.json()
console.log(data.choices?.[0]?.message?.content)

Python

import os
import requests

response = requests.post(
    'https://api.gemai.cc/v1/chat/completions',
    headers={
        'Authorization': f"Bearer {os.environ['GEMAI_API_KEY']}",
        'Content-Type': 'application/json',
    },
    json={
        'model': '[官逆]gemini-2.5-pro',
        'messages': [
            {'role': 'user', 'content': '你好，请介绍一下你自己。'},
        ],
    },
    timeout=120,
)

response.raise_for_status()
print(response.json()['choices'][0]['message']['content'])

返回示例

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "model": "[官逆]gemini-2.5-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！我可以帮助你进行文本创作、代码编写、问题解答等。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 19,
    "completion_tokens": 20,
    "total_tokens": 39
  }
}

注意事项

• OpenAI SDK 的 baseURL 填 https://api.gemai.cc/v1。
• 流式输出时在请求体中加入 "stream": true。
• 图片输入需要选择支持视觉能力的模型。