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

# Qwen Image

> Use Qwen Image series models for text-to-image, and the client continues to use the OpenAI Images compatible protocol

> Content updated: 2026-06-06

# Qwen Image

```
POST /v1/images/generations
```

Crazyrouter currently opens to the public an OpenAI Images compatible protocol, `Qwen Image`, for the first batch of generation models. Customers continue to use the unified `/v1/images/generations`, and Alibaba official and third-party providers only serve as internal providers and do not expose client protocols separately.

## Models Currently Open

| Model | Upstream Execution Mode | Current Client Capability | Verification Status |
| - | - | - | - |
| `qwen-image-plus` | Asynchronous Generation | Text-to-image | Verified |
| `qwen-image-max` | Synchronous Generation | Text-to-image | Verified |
| `qwen-image-2.0` | Synchronous Generation | Text-to-image | Verified |
| `qwen-image-2.0` | Synchronous Generation | Text-to-image | Beta |

> [!NOTE]
>
> `qwen-image-2.0` has now completed protocol and code alignment, but production evidence is still being supplemented, so it is temporarily marked as Beta.

## Client Protocol

### Request Parameters

| Parameter | Type | Required | Description |
| - | - | - | - |
| `model` | string | Yes | `qwen-image-plus`, `qwen-image-max`, `qwen-image-2.0`, `qwen-image-2.0` |
| `prompt` | string | Yes | Text-to-image prompt |
| `size` | string | No | Output size. It is recommended to use supported sizes listed on the current model page or playground |
| `n` | integer | No | Number of images generated, default is `1` |
| `response_format` | string | No | `url` or `b64_json` |

### Request Example

```bash cURL theme={null}
curl -X POST https://api.crazyrouter.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen-image-max",
    "prompt": "一张具有高级感的产品海报，主体是一瓶玻璃香水，柔和棚拍光线，中文标题“晨雾”",
    "size": "1024x1024",
    "n": 1,
    "response_format": "url"
  }'
```

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

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.crazyrouter.com/v1"
)

response = client.images.generate(
    model="qwen-image-max",
    prompt="一张具有高级感的产品海报，主体是一瓶玻璃香水，柔和棚拍光线，中文标题“晨雾”",
    size="1024x1024",
    n=1
)

print(response.data[0].url)
```

### Response Example

```json theme={null}
{
  "created": 1709123456,
  "data": [
    {
      "url": "https://crazyrouter.com/files/qwen_image_abc123.png"
    }
  ]
}
```

## Official Billing Standard

Currently, Qwen Image is officially billed based on the number of images successfully generated, not based on input/output token display.

| Model | Official Standard | Official Unit Price | Current Documentation Status |
| - | - | - | - |
| `qwen-image-plus` | Per Image | `¥0.20 per image` | Verified |
| `qwen-image-max` | Per Image | `¥0.50 per image` | Verified |
| `qwen-image-2.0` | Per Image | `¥0.20 per image` | Verified |
| `qwen-image-2.0` | Per Image | `¥0.50 per image` | Beta |

## Boundary Notes

* This page only promises `Text to Image` client capability for the first batch; additional upstream multi-modal capabilities are not directly exposed in the client protocol.
* Providers on `Qwen Image` may have asynchronous or synchronous differences, but the client side still uses the unified OpenAI Images request/response format.
* The image editing model `qwen-image-plus` is not in the scope of “generation model convergence” for this batch on this page; if editing capability is required, please evaluate separately according to the currently open status of the editing model.

## Related Pages

* [Qwen Image 2.0 Model Page: Real-time Price, Real Samples, Calling Code](https://crazyrouter.com/en/models/alibaba/qwen-image-2-0?utm_source=docs\&utm_medium=related)
* [Alibaba Cloud All Models and Prices](https://crazyrouter.com/en/models/alibaba?utm_source=docs\&utm_medium=related)


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