Aliyun Image Generation

Create images using the Alibaba Cloud Model Studio / DashScope image format. Use the official model, input.messages, and parameters request structure; the platform only provides a unified endpoint, authentication, model routing, and billing.

Supported Models

This endpoint is only for Alibaba Cloud Model Studio / DashScope image generation or editing models, and it only routes to Aliyun channels configured on the platform. The examples follow these official model families:

Model / Family	Use case	Notes
qwen-image-2.0-pro, qwen-image-2.0	Qwen text-to-image	Pass prompts in messages[].content[].text
qwen-image-max, qwen-image-plus, qwen-image	Qwen text-to-image	Pass prompts in messages[].content[].text
wan2.6-image	Wanxiang image generation and editing	Use text and optional image items in messages[].content[]

For non-Aliyun image models, such as OpenAI, Volcengine Seedream, or Gemini models, use the matching image endpoint instead of this one.

Try It

POST/aliyun/v1/images/generationshttps://api-platform.ope.ai

Authentication

Uses Bearer Token authentication.

• Header: Authorization: Bearer <token>
• Example: Authorization: Bearer sk-xxxxxx

Request body (application/json)

Field	Type	Required	Description	Default / Range
model	string	Yes	Alibaba Cloud Model Studio / DashScope image model ID. The platform may map it through channel configuration	Examples: qwen-image-2.0-pro, qwen-image, wan2.6-image
input	object	Yes	Image generation input	-
parameters	object	No	Generation parameters	-

input

Field	Type	Required	Description
messages	array<object>	Yes	Request content array. The official Aliyun docs currently describe single-turn input

messages

Field	Type	Required	Description
role	string	Yes	Fixed to user
content	array<object>	Yes	Message content array

content

Field	Type	Required	Description
text	string	Yes	Positive prompt. Qwen-Image text-to-image and Wan2.6 Image both use one text item in content in the official docs
image	string	No	Wan2.6 Image reference image. Supports public image URLs or Base64 image strings

parameters

Field	Type	Required	Description	Default / Range
size	string	No	Output size. Use Aliyun's official width*height format, such as 2048*2048 or 1280*1280; Wan2.6 Image also supports 1K and 2K	Official model default
n	integer	No	Number of output images	Official model limit
negative_prompt	string	No	Negative prompt	-
prompt_extend	boolean	No	Whether to enable prompt rewriting	Official model default
watermark	boolean	No	Whether to add a watermark	Official model default
seed	integer	No	Qwen-Image random seed	0 to 2147483647
enable_interleave	boolean	No	Wan2.6 Image interleaved text-image output mode	false
max_images	integer	No	Maximum generated images in Wan2.6 Image interleaved mode	Official model limit
stream	boolean	No	Required with streaming output for Wan2.6 Image interleaved synchronous calls	Follow the official model docs

Request examples

The domain below is an example: https://api-platform.ope.ai.

cURL

curl -X POST "https://api-platform.ope.ai/aliyun/v1/images/generations" \
  -H "Authorization: Bearer $OPEAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-2.0-pro",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "text": "A white mechanical cat sitting beside a minimal desk, cinematic lighting, high detail."
            }
          ]
        }
      ]
    },
    "parameters": {
      "size": "2048*2048",
      "n": 1,
      "prompt_extend": true,
      "watermark": false
    }
  }'

JavaScript

const apiKey = process.env.OPEAI_API_KEY;

const res = await fetch("https://api-platform.ope.ai/aliyun/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "qwen-image-2.0-pro",
    input: {
      messages: [
        {
          role: "user",
          content: [
            {
              text: "A white mechanical cat sitting beside a minimal desk, cinematic lighting, high detail.",
            },
          ],
        },
      ],
    },
    parameters: {
      size: "2048*2048",
      n: 1,
      prompt_extend: true,
      watermark: false,
    },
  }),
});

console.log(await res.json());

Python

import os
import requests

resp = requests.post(
  "https://api-platform.ope.ai/aliyun/v1/images/generations",
  headers={
    "Authorization": f"Bearer {os.environ.get('OPEAI_API_KEY')}",
    "Content-Type": "application/json",
  },
  json={
    "model": "qwen-image-2.0-pro",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "text": "A white mechanical cat sitting beside a minimal desk, cinematic lighting, high detail.",
            },
          ],
        },
      ],
    },
    "parameters": {
      "size": "2048*2048",
      "n": 1,
      "prompt_extend": True,
      "watermark": False,
    },
  },
  timeout=120,
)

print(resp.json())

Reference image

{
  "model": "wan2.6-image",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Use this product image as reference and generate a clean ecommerce hero image."
          },
          {
            "type": "image",
            "image": "https://example.com/reference.png"
          }
        ]
      }
    ]
  },
  "parameters": {
    "size": "1K",
    "prompt_extend": true,
    "enable_interleave": false,
    "n": 1
  }
}

Response examples

The platform passes through the Aliyun upstream response body. Successful responses typically include output.choices[]; the platform uses the generated image count from the upstream response for billing.

Success

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "role": "assistant",
          "content": [
            {
              "image": "https://dashscope-result.example.com/generated-image.png"
            }
          ]
        }
      }
    ]
  },
  "usage": {
    "image_count": 1,
    "width": 2048,
    "height": 2048
  },
  "request_id": "8f0b9c7a-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Error

{
  "error": {
    "message": "only aliyun channel is supported on /aliyun/v1/images/generations",
    "type": "invalid_request_error",
    "code": "invalid_request"
  }
}

Notes

• This endpoint only supports Alibaba Cloud Model Studio / DashScope image models and only routes to Aliyun channels. If the model cannot match an Aliyun channel, the platform returns an error.
• Request fields, value ranges, image input limits, and response shape should follow the official Aliyun documentation for the selected model.