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

# Qwen3.6-Flash

> 通过 Starrise AI 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 Starrise AI 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

```bash cURL theme={null}
curl https://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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://dayu.cdn-fly.com/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
  }'
```

> **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` |

> **[API 参考](/zh/api-reference/model-api/alibaba/qwen3.6-flash)**
>
> 查看 Qwen3.6-Flash 的交互式 API Playground。


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.