> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aihubmix.com/llms.txt
> Use this file to discover all available pages before exploring further.

# 阿里通義系列

## Qwen 3 系列

Qwen3 系列是阿里推出的新一代開源大模型，能力大幅躍升：在代碼理解、數學推理、多語言表達、複雜推斷任務上，比肩甚至超越了目前市面上的頂級模型（如 o1、DeepSeek-R1）。**它的核心突破在于引入了「思考模式」與「非思考模式」切換機制，讓模型在面對不同難度任務時，自主調節推理深度，實現了速度與精度的雙優平衡。** 旗艦版 Qwen3-235B 採用稀疏激活，僅用 22B 參數推理，兼顧成本和卓越能力。全系模型全面開源，涵蓋從輕量到超大規模需求。

**1. 基礎用法：** 用 OpenAI 兼容格式轉發。\
**2. 工具調用：** 常規 Tools 調用支持 OpenAI 兼容格式（適用於 V2.5、V3），而 MCP Tools 依賴 `qwen-agent`，需要先運行指令安裝依賴：`pip install -U qwen-agent mcp`。
更多細節可以參考[阿里官方文件](https://huggingface.co/Qwen/Qwen3-235B-A22B)

<CodeGroup>
  ```py 基礎用法 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-***", # 🔑 換成你在 AiHubMix 生成的密鑰
      base_url="https://aihubmix.com/v1",
  )

  completion = client.chat.completions.create(
      model="Qwen/Qwen3-30B-A3B",
      messages=[
          {
              "role": "user",
              "content": "Explain the Occam's Razor concept and provide everyday examples of it"
          }
      ],
      stream=True
  )

  # 某些 chunk 物件可能沒有 choices 屬性或 choices 是一個空列表，處理方法：
  for chunk in completion:
      if hasattr(chunk.choices, '__len__') and len(chunk.choices) > 0:
          if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content is not None:
              print(chunk.choices[0].delta.content, end="")
  ```

  ```py Tools theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-***", # 🔑 換成你在 AiHubMix 生成的密鑰
      base_url="https://aihubmix.com/v1",
  )

  # 定義工具
  tools = [
      {
          "type": "function",
          "function": {
              "name": "get_current_weather",
              "description": "獲取指定位置的當前天氣",
              "parameters": {
                  "type": "object",
                  "properties": {
                      "location": {
                          "type": "string",
                          "description": "城市名稱，如北京、上海等"
                      },
                      "unit": {
                          "type": "string",
                          "enum": ["celsius", "fahrenheit"],
                          "description": "溫度單位"
                      }
                  },
                  "required": ["location"]
              }
          }
      }
  ]

  # 創建聊天完成請求，包含工具定義
  completion = client.chat.completions.create(
      model="Qwen/Qwen3-30B-A3B", #2.5 和 3 都支持，QwQ 不支持
      messages=[
          {
              "role": "user",
              "content": "北京今天的天氣怎麼樣？"
          }
      ],
      tools=tools,
      tool_choice="auto",  # 讓模型自行決定是否使用工具
      stream=True
  )

  # 用於收集工具調用信息的字典
  tool_calls = {}

  # 處理流式響應
  for chunk in completion:
      if not hasattr(chunk.choices, '__len__') or len(chunk.choices) == 0:
          continue
          
      delta = chunk.choices[0].delta
      
      # 處理文本內容
      if hasattr(delta, 'content') and delta.content:
          print(delta.content, end="")
      
      # 處理工具調用
      if hasattr(delta, 'tool_calls') and delta.tool_calls:
          for tool_call in delta.tool_calls:
              if not hasattr(tool_call, 'index'):
                  continue
                  
              idx = tool_call.index
              if idx not in tool_calls:
                  tool_calls[idx] = {"name": "", "arguments": ""}
                  
              if hasattr(tool_call, 'function'):
                  if hasattr(tool_call.function, 'name') and tool_call.function.name:
                      tool_calls[idx]["name"] = tool_call.function.name
                  if hasattr(tool_call.function, 'arguments') and tool_call.function.arguments:
                      tool_calls[idx]["arguments"] += tool_call.function.arguments

  # 完成後，打印收集到的工具調用信息
  for idx, info in tool_calls.items():
      if info["name"]:
          print(f"\n工具調用：{info['name']}")
      if info["arguments"]:
          print(f"參數：{info['arguments']}")

  ```

  ```py MCP Tools theme={null}
  from qwen_agent.agents import Assistant
  import os

  # Define LLM
  llm_cfg = {
      'model': 'Qwen/Qwen3-30B-A3B',

      # Use a custom endpoint compatible with OpenAI API:
      'model_server': 'https://aihubmix.com/v1',
      'api_key': os.getenv('AIHUBMIX_API_KEY'),

      # Other parameters:
      # 'generate_cfg': {
      #         # Add: When the response content is `<think>this is the thought</think>this is the answer;
      #         # Do not add: When the response has been separated by reasoning_content and content.
      #         'thought_in_content': True,
      #     },
  }

  # Define Tools
  tools = [
      {'mcpServers': {  # You can specify the MCP configuration file
              'time': {
                  'command': 'uvx',
                  'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
              },
              "fetch": {
                  "command": "uvx",
                  "args": ["mcp-server-fetch"]
              }
          }
      },
    'code_interpreter',  # Built-in tools
  ]

  # Define Agent
  bot = Assistant(llm=llm_cfg, function_list=tools)

  # Streaming generation
  messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
  for responses in bot.run(messages=messages):
      pass
  print(responses)
  ```
</CodeGroup>

## QvQ、Qwen 2.5 和 QwQ 系列

用 OpenAI 的兼容格式轉發即可，區別在於流式調用的提取，需要剔除為空的 `chunk.choices[0].delta.content`，參考如下。

**1. QvQ、Qwen 2.5 VL：** 圖片認識\
**2. QwQ：** 文本任務

<Info>
  `Qwen/QVQ-72B-Preview` 是基于 `Qwen2-VL-72B` 構建的开源多模態推理模型，专注于视觉推理和跨模態任务。
</Info>

<CodeGroup>
  ```py Qwen 2.5 VL theme={null}
  from openai import OpenAI
  import base64
  import os

  client = OpenAI(
      api_key="sk-***", # 🔑 換成你在 AiHubMix 生成的密鑰
      base_url="https://aihubmix.com/v1",
  )

  image_path = "yourpath/file.png"

  # 讀取並編碼圖片
  def encode_image(image_path):
      if not os.path.exists(image_path):
          raise FileNotFoundError(f"圖片文件不存在：{image_path}")
      
      with open(image_path, "rb") as image_file:
          return base64.b64encode(image_file.read()).decode('utf-8')

  # 獲取圖片的 base64 編碼
  base64_image = encode_image(image_path)

  # 創建包含文本和圖像的消息
  completion = client.chat.completions.create(
      model="qwen2.5-vl-72b-instruct", #qwen2.5-vl-72b-instruct 或 Qwen/QVQ-72B-Preview
      messages=[
          {
              "role": "user",
              "content": [
                  {"type": "text", "text": "請詳細描述這張圖片，包括圖片中的內容、風格和可能的含義。"},
                  {
                      "type": "image_url",
                      "image_url": {
                          "url": f"data:image/png;base64,{base64_image}"
                      }
                  }
              ]
          }
      ],
      stream=True
  )

  for chunk in completion:
      # 安全地檢查是否有內容
      if hasattr(chunk.choices, '__len__') and len(chunk.choices) > 0:
          if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content is not None:
              print(chunk.choices[0].delta.content, end="")
  ```

  ```py QwQ theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-***", # 🔑 換成你在 AiHubMix 生成的密鑰
      base_url="https://aihubmix.com/v1",
  )

  completion = client.chat.completions.create(
      model="Qwen/QwQ-32B",
      messages=[
          {
              "role": "user",
              "content": [
                  {"type": "text", "text": "支配宇宙的元規則是什么？"}
              ]
          }
      ],
      stream=True
  )

  for chunk in completion:
      if hasattr(chunk.choices, '__len__') and len(chunk.choices) > 0:
          if hasattr(chunk.choices[0].delta, 'content') and chunk.choices[0].delta.content is not None:
              print(chunk.choices[0].delta.content, end="")
  ```
</CodeGroup>

***

最後更新：2026-06-01