使用代码进行调用的示例

/v1/chat/completions 格式

这是 OpenAI 标准的聊天补全接口格式，主要使用 messages 数组来传递上下文。

Python 示例

import requests

url = "https://beta2.meeta.tech/v1/chat/completions"
headers = {
    "Authorization": "Bearer 您生成的令牌",
    "Content-Type": "application/json"
}
payload = {
    "model": "gpt-5.4",
    "messages": [
        {"role": "system", "content": "你是一个有用的AI助手。"},
        {"role": "user", "content": "你好，请简要介绍一下你自己。"}
    ],
    "temperature": 0.7
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

cURL 示例

curl -X POST "https://beta2.meeta.tech/v1/chat/completions" \
     -H "Authorization: Bearer 您生成的令牌" \
     -H "Content-Type: application/json" \
     -d '{
           "model": "gpt-5.4",
           "messages": [
               {"role": "system", "content": "你是一个有用的AI助手。"},
               {"role": "user", "content": "你好，请简要介绍一下你自己。"}
           ],
           "temperature": 0.7
         }'

---

/v1/responses 格式

OpenAI 最先进的模型响应接口。支持文本和图像输入，以及文本输出

Python 示例

import requests

url = "https://beta2.meeta.tech/v1/responses"
headers = {
    "Authorization": "Bearer 您生成的令牌",
    "Content-Type": "application/json"
}
payload = {
  "model": "gpt-5.4",
  "stream": false,
  "input": [
    {
      "role": "user",
      "content": "写一篇睡前故事"
    }
  ]
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

cURL 示例

curl -X POST "https://beta2.meeta.tech/v1/responses" \
     -H "Authorization: Bearer 您生成的令牌" \
     -H "Content-Type: application/json" \
     -d '{
            "model": "gpt-5.4",
            "stream": false,
            "input": [
                {
                "role": "user",
                "content": "写一篇睡前故事"
                }
            ]
        }'

---

/v1/messages 格式

这是 Anthropic (Claude) 标准的 API 格式。它与 OpenAI 的区别在于请求头通常需要传入 API Key 和版本号，且 max_tokens 是必填参数。(注：如果您使用的反代服务兼容了 OpenAI 的 Authorization 请求头，请相应替换 x-api-key)

Python 示例

import requests

url = "https://beta2.meeta.tech/v1/messages"
headers = {
    "x-api-key": "您生成的令牌",
    "anthropic-version": "2023-06-01",
    "Content-Type": "application/json"
}
payload = {
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [
        {"role": "user", "content": "你好，请帮我检查一段Python代码。"}
    ]
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())

cURL 示例

curl -X POST "https://beta2.meeta.tech/v1/messages" \
     -H "x-api-key: 您生成的令牌" \
     -H "anthropic-version: 2023-06-01" \
     -H "Content-Type: application/json" \
     -d '{
           "model": "claude-sonnet-4-6",
           "max_tokens": 1024,
           "messages": [
               {"role": "user", "content": "你好，请帮我检查一段Python代码。"}
           ]
         }'

/v1beta/models/{model}:generateContent 格式

这是 Google Gemini 原生 API 的标准调用格式。它使用 contents 数组来传递消息，每条消息包含 role 和由 parts（通常是包含 text 的对象）组成的数组。模型的参数配置通常放在 generationConfig 中。

Python 示例

import requests

# 注意：Gemini 的原生路径通常将模型名称包含在 URL 中
url = "https://beta2.meeth.tech/v1beta/models/gemini-3.1-pro-preview:generateContent"
headers = {
    "x-goog-api-key": "您生成的令牌",
    "Content-Type": "application/json"
}
payload = {
    "contents": [
        {
            "role": "user",
            "parts": [
                {"text": "你好，请简要介绍一下你自己。"}
            ]
        }
    ],
    "generationConfig": {
        "temperature": 0.7,
        "maxOutputTokens": 1024
    }
}

response = requests.post(url, headers=headers, json=payload)
print(response.json())