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

# Qwen3.6-Flash

> 通过 AnyFast OpenAI 兼容接口调用阿里巴巴 Qwen3.6-Flash 视觉语言模型。快速、智能体友好的多模态模型。

Qwen3.6-Flash 是阿里巴巴的原生视觉语言 Flash 模型，通过 AnyFast 以 OpenAI 兼容接口提供。相比 Qwen3.5-Flash，在智能体编码、数学/代码推理和空间智能方面有显著提升。

## 核心能力

* **OpenAI 兼容** — 可直接替换 OpenAI SDK，无需修改其他代码
* **100 万 Token 上下文** — 支持大规模文档和多轮对话，最多 66K 输出 Token
* **多模态输入** — 支持文本、图片和视频输入
* **智能体编码** — 编码 Agent 基准测试大幅提升
* **推理能力** — 通过 `enable_thinking` 参数启用内置思维链
* **内置工具** — 通过 Responses API 支持联网搜索、代码解释器、网页抓取、图片搜索

## 快速示例

<CodeGroup>
  ```bash cURL theme={null}
  curl https://www.anyfast.ai/v1/chat/completions \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "qwen3.6-flash",
      "messages": [
        { "role": "user", "content": "用简单的语言解释量子纠缠。" }
      ]
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  response = client.chat.completions.create(
      model="qwen3.6-flash",
      messages=[
          {"role": "user", "content": "用简单的语言解释量子纠缠。"}
      ]
  )

  print(response.choices[0].message.content)
  ```

  ```python 流式输出 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  stream = client.chat.completions.create(
      model="qwen3.6-flash",
      messages=[
          {"role": "user", "content": "写一首关于大海的短诗。"}
      ],
      stream=True
  )

  for chunk in stream:
      print(chunk.choices[0].delta.content or "", end="")
  ```

  ```python 推理模式 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  completion = client.chat.completions.create(
      model="qwen3.6-flash",
      messages=[
          {"role": "user", "content": "解这道数学题：x² + 5x + 6 = 0，求 x。"}
      ],
      extra_body={"enable_thinking": True},
      stream=True
  )

  for chunk in completion:
      if chunk.choices and chunk.choices[0].delta:
          delta = chunk.choices[0].delta
          if hasattr(delta, "reasoning_content") and delta.reasoning_content:
              print(delta.reasoning_content, end="", flush=True)
          if delta.content:
              print(delta.content, end="", flush=True)
  ```

  ```python 图片输入 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  response = client.chat.completions.create(
      model="qwen3.6-flash",
      messages=[
          {
              "role": "user",
              "content": [
                  {"type": "text", "text": "请描述这张图片。"},
                  {
                      "type": "image_url",
                      "image_url": {
                          "url": "https://example.com/photo.jpg"
                          # 或 base64: "url": "data:image/png;base64,iVBORw0KGgo..."
                      }
                  }
              ]
          }
      ],
      max_completion_tokens=300
  )

  print(response.choices[0].message.content)
  ```

  ```python 视频输入 theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="YOUR_API_KEY",
      base_url="https://www.anyfast.ai/v1"
  )

  response = client.chat.completions.create(
      model="qwen3.6-flash",
      messages=[
          {
              "role": "user",
              "content": [
                  {"type": "text", "text": "请总结这个视频的内容。"},
                  {
                      "type": "video_url",
                      "video_url": {
                          "url": "https://example.com/sample.mp4"
                          # 或 base64: "url": "data:video/mp4;base64,AAAAIGZ0eXBpc29t..."
                      }
                  }
              ]
          }
      ],
      max_completion_tokens=300
  )

  print(response.choices[0].message.content)
  ```

  ```bash cURL (图片) theme={null}
  curl https://www.anyfast.ai/v1/chat/completions \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "qwen3.6-flash",
      "messages": [
        {
          "role": "user",
          "content": [
            {"type": "text", "text": "请描述这张图片。"},
            {"type": "image_url", "image_url": {"url": "data:image/png;base64,iVBORw0KGgo..."}}
          ]
        }
      ],
      "max_completion_tokens": 300
    }'
  ```
</CodeGroup>

> **注意：** `image_url` 和 `video_url` 同时支持远程 URL (`https://...`) 和 base64 数据 URI (`data:image/png;base64,...` / `data:video/mp4;base64,...`)。图片 tokens 和视频 tokens 会在 `usage.prompt_tokens_details` 中体现。

## 参数说明

| 参数                      | 类型      | 必填 | 说明                                                          |
| ----------------------- | ------- | -- | ----------------------------------------------------------- |
| `model`                 | string  | 是  | 固定为 `qwen3.6-flash`                                         |
| `messages`              | array   | 是  | `{ role, content }` 对象数组。支持 `image_url` 和 `video_url` 多模态输入 |
| `max_completion_tokens` | integer | 否  | 最大生成 Token 数                                                |
| `temperature`           | float   | 否  | `0`–`2`，控制随机性，默认 `1`                                        |
| `stream`                | boolean | 否  | 开启 SSE 流式传输，默认 `false`                                      |
| `top_p`                 | float   | 否  | 核采样阈值，默认 `1`                                                |
| `stop`                  | array   | 否  | 停止序列。必须为数组格式，默认 `null`                                      |
| `enable_thinking`       | boolean | 否  | 通过 `extra_body` 启用推理模式，默认 `false`                           |

<Card title="API 参考" icon="code" href="/zh/api-reference/model-api/alibaba/qwen3.6-flash">
  查看 Qwen3.6-Flash 的交互式 API Playground。
</Card>

<script src="/feedback.js" />