> ## 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.

# Openai Responses API 支援

支援 Openai 的 Responses API 多功能介面，已經上線的功能介面如下：

* Text input：文字輸入
* Image input：圖文輸入
* Streaming：串流調用
* Web search：搜尋
* Reasoning：推理深度控制，支援 4 個等級（minimal / low / medium / high）。其中 minimal 僅適用於 gpt-5 系列。
* Verbosity：輸出長度（冗長度），gpt-5 系列支援 3 個等級（low / medium / high）
* Functions：函數調用
* image\_generation：繪圖工具調用，圖片生成部分按 `gpt-image-1` 計價
* Code Interpreter：程式碼解析器
* Remote MCP：MCP 調用
* Computer Use：自動操作

## 使用（Python 調用）：

與官方的 OpenAI 調用方式一致，只需替換 `api_key` 和 `base_url` 進行轉發。
中國大陸可直接連線訪問。

```py theme={null}
client = OpenAI(
    api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
    base_url="https://aihubmix.com/v1"
)
```

對於推理模型，支援通過以下參數來輸出推理總結，總結細節的豐富程度為 detailed > auto > None，其中 auto 為最佳平衡。

```py theme={null}
"summary": "auto" 
```

<CodeGroup>
  ```py GPT-5 系列 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-***", # 將其替換為你在 AIHubMix 後台產生的金鑰
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
      model="gpt-5", # gpt-5, gpt-5-chat-latest, gpt-5-mini, gpt-5-nano
      input="為什麼塔羅占卜有效？其背後的原理是什麼？有哪些可遷移的方法？輸出格式：Markdown", # GPT-5 預設不以 Markdown 格式輸出，因此需要明確指定。
      reasoning={
          "effort": "minimal" # 推理深度——控制模型在產生回覆前會生成多少推理 token。可用值為 "minimal"、"low"、"medium" 或 "high"。預設為 "medium"。
      },
      text={
          "verbosity": "low" # 輸出長度——冗長度決定會生成多少輸出 token。可用值為 "low"、"medium" 或 "high"。GPT-5 之前的模型預設為 "medium" 冗長度。
      },
      stream=True
  )

  for event in response:
    print(event)
  ```

  ```py 文字 theme={null}
  from openai import OpenAI
  import os

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
    model="gpt-4o-mini", # codex-mini-latest 可用
    input="Tell me a three sentence bedtime story about a unicorn."
  )

  print(response)
  ```

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

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
      model="gpt-4o-mini", # codex-mini-latest 可用
      input=[
          {
              "role": "user",
              "content": [
                  { "type": "input_text", "text": "what is in this image?" },
                  {
                      "type": "input_image",
                      "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
                  }
              ]
          }
      ]
  )

  print(response)
  ```

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

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
    model="gpt-4o-mini", # codex-mini-latest 可用
    instructions="You are a helpful assistant.",
    input="Hello!",
    stream=True
  )

  for event in response:
    print(event)
  ```

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

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
    model="gpt-4o-mini", # codex-mini-latest 不支援搜尋📍
    tools=[{ "type": "web_search_preview" }],
    input="What was a positive news story from today?",
  )

  print(response)
  ```

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

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1/"
  )

  response = client.responses.create(
      model="o4-mini", # 支援 codex-mini-latest, o4-mini, o3-mini, o3, o1
      input="How much wood would a woodchuck chuck?",
      reasoning={
          "effort": "medium", # 支援 low, medium, high
          "summary": "auto" # 推理總結
      }
  )

  print(response)
  ```

  ```py 函數調用 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  tools = [
      {
          "type": "function",
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location", "unit"],
          }
      }
  ]

  response = client.responses.create(
    model="gpt-4o-mini", # codex-mini-latest 可用
    tools=tools,
    input="What is the weather like in Boston today?",
    tool_choice="auto"
  )

  print(response)
  ```

  ```py 圖片生成工具 theme={null}
  from openai import OpenAI
  import base64

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  response = client.responses.create(
      model="gpt-4.1-mini",
      input="Generate an image of gray tabby cat hugging an otter with an orange scarf",
      tools=[{"type": "image_generation"}],
  )

  # 儲存為圖片檔案
  image_data = [
      output.result
      for output in response.output
      if output.type == "image_generation_call"
  ]

  if image_data:
      image_base64 = image_data[0]
      with open("cat_and_otter.png", "wb") as f:
          f.write(base64.b64decode(image_base64))
  ```

  ```py 程式碼解析器 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  instructions = """
  You are a personal math tutor. When asked a math question, 
  write and run code using the python tool to answer the question.
  """

  resp = client.responses.create(
      model="gpt-4.1",
      tools=[
          {
              "type": "code_interpreter",
              "container": {"type": "auto"}
          }
      ],
      instructions=instructions,
      input="I need to solve the equation 3x + 11 = 14. Can you help me?",
  )

  print(resp.output)
  ```

  ```py Remote MCP theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="AIHUBMIX_API_KEY", # 換成你在後台生成的 Key "sk-***"
      base_url="https://aihubmix.com/v1"
  )

  resp = client.responses.create(
      model="gpt-4.1",
      tools=[{
          "type": "mcp",
          "server_label": "deepwiki",
          "server_url": "https://mcp.deepwiki.com/mcp",
          "require_approval": "never",
          "allowed_tools": ["ask_question"],
      }],
      input="What transport protocols does the 2025-03-26 version of the MCP spec (modelcontextprotocol/modelcontextprotocol) support?",
  )

  print(resp.output_text)
  ```
</CodeGroup>

**注意：**

1. 最新的 `codex-mini-latest` 不支援搜尋
2. Computer use 需要配合 Praywright 使用，建議參考[官方倉庫](https://github.com/openai/openai-cua-sample-app)

已知細節問題：

* 調用用例複雜
* 截圖大量，耗時久，任務成功率低
* 或觸發 CAPTCHA 驗證或 Cloudflare 真人驗證，可能遇到無限循環

***

最後更新：2026-06-01