Qwen 3.7 API

Alibaba 提供支援的 Qwen 3.7 LLM 模型完整 API 參考。

模型變體

此 API 支援四個 Qwen 3.7 模型變體：

快速對比

Qwen 3.7 Max Text to Text

端點

http複製
POST /api/v1/chat/completions

請求參數

必填

訊息支援

可選

範例請求

javascript複製
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Accept': 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'qwen-3.7-max-text-to-text',
    messages: [
      {
        role: 'user',
        content: 'Explain the concept of attention mechanisms in neural networks.'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});

Qwen 3.7 Plus Text to Text

端點

http複製
POST /api/v1/chat/completions

請求參數

必填

訊息支援

可選

範例請求

javascript複製
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Accept': 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'qwen-3.7-plus-text-to-text',
    messages: [
      {
        role: 'user',
        content: 'Explain the concept of attention mechanisms in neural networks.'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});

Qwen 3.7 Max Web Search

端點

http複製
POST /api/v1/chat/completions

請求參數

必填

訊息支援

可選

範例請求

javascript複製
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Accept': 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'qwen-3.7-max-web-search',
    messages: [
      {
        role: 'user',
        content: 'What are the latest developments in quantum computing this year?'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});

Qwen 3.7 Plus Web Search

端點

http複製
POST /api/v1/chat/completions

請求參數

必填

訊息支援

可選

範例請求

javascript複製
const response = await fetch('https://api.flaq.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Accept': 'text/event-stream',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'qwen-3.7-plus-web-search',
    messages: [
      {
        role: 'user',
        content: 'What are the latest developments in quantum computing this year?'
      }
    ],
    stream: true,
    max_tokens: 2048
  })
});

回應格式

Qwen 3.7 LLM models return OpenAI-compatible completion responses. With stream: true, the response is Server-Sent Events; with stream: false, the response is a single JSON object.

成功回應

text複製
data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"qwen-3.7-max-text-to-text","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"qwen-3.7-max-text-to-text","choices":[{"index":0,"delta":{"content":"Here is a concise explanation"},"finish_reason":null}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"qwen-3.7-max-text-to-text","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","created":1710000000,"model":"qwen-3.7-max-text-to-text","choices":[],"usage":{"prompt_tokens":12,"completion_tokens":8,"total_tokens":20}}

data: [DONE]

錯誤回應

text複製
event: error
data: {"error":{"message":"API requests too frequent, exceeding rate limit","type":"rate_limit_error","code":"1302","param":null}}

最佳實務

1. 使用結構化訊息： 透過 messages[] 傳送對話歷史，而不是把上下文壓平成單一 prompt。
2. 選擇合適的變體： 複雜推理任務使用 Max，快速且高性價比的回應使用 Plus。需要最新資訊時使用 Web Search 變體。
3. 處理 SSE 事件： 串流顯示時追加 choices[0].delta.content，並將 data: [DONE] 視為成功完成。
4. 僅傳送支援的輸入： Qwen 3.7 模型僅支援文字，不支援檔案或圖片附件。