Test Image & Video Generation APIs with Postman or cURL - Model Studio

Image and video generation tasks can take tens of seconds to several minutes. These APIs use an asynchronous two-step pattern to prevent HTTP timeouts: create a task, then poll for the result.

Choose a tool:

Postman: Graphical HTTP client (best for beginners)
cURL: Command-line HTTP client (best for terminal users)

Postman and cURL are for quick testing only. For production, use the official SDK or build your own HTTP client.

How asynchronous generation works

All image and video generation APIs follow a two-step async pattern:

Create a task -- Send a POST request with your prompt and parameters. The API returns a task_id.
Poll for the result -- Send GET requests with the task_id until task_status is SUCCEEDED. The response then contains the output URL.

Task status reference

Status	Meaning	Action
`RUNNING`	The task is in progress.	Poll again in 3-5 seconds.
`SUCCEEDED`	Generation is complete.	Retrieve the output URL from the response.

Important

Both task_id and the output image URL expire after 24 hours. Download the result promptly.

Send requests with Postman

Prerequisites

Before you begin:

A Model Studio API key
Postman installed

cURL-to-Postman parameter mapping

Use the following table to convert a cURL example into a Postman request:

cURL syntax	Postman location	Purpose
`curl -X POST` or `curl -X GET`	Request method drop-down	HTTP method
`https://<url>`	URL input field	API endpoint
`-H 'Key: Value'`	Headers tab	Request headers
`-d '{...}'`	Body tab	Request body (JSON)

Step 1: Create a task

The following cURL command shows the equivalent request you will configure in Postman:

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wan2.5-t2i-preview",
    "input": {
        "prompt": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"
    },
    "parameters": {
        "size": "1024*1024",
        "n": 1
    }
}'

Different regions use separate base_urls.

Configure the request in Postman:

Click + to create a new HTTP request.
Set method to POST and enter the endpoint URL:
- Singapore: https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis
- Virginia: https://dashscope-us.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis
- Beijing: https://dashscope.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis

In the Headers tab, add:

Key	Value	Purpose
`X-DashScope-Async`	`enable`	Enable asynchronous mode
`Authorization`	`Bearer <your-api-key>`	Authentication. Replace `<your-api-key>` with your Model Studio API key.
`Content-Type`	`application/json`	Specify JSON request body

Configure request headers

In the Body tab, select raw → JSON, then paste:

   {
       "model": "wan2.5-t2i-preview",
       "input": {
           "prompt": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"
       },
       "parameters": {
           "size": "1024*1024",
           "n": 1
       }
   }

Configure request body

Click Send. The response contains a task_id — save it for Step 2.

Step 2: Poll for the result

Use the task_id from Step 1 to query task status.

Equivalent cURL command:

curl -X GET https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Configure the query request in Postman:

Create a new HTTP request and set method to GET.
Enter the query URL. Replace {task_id} with the value from Step 1:
- Singapore: https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}
- Virginia: https://dashscope-us.aliyuncs.com/api/v1/tasks/{task_id}
- Beijing: https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}
In the Headers tab, add the Authorization key (same API key as Step 1).
Click Send.

Query task status in Postman

If task_status is RUNNING, wait 3-5 seconds and click Send again. When SUCCEEDED, copy the image URL.

Important

The image URL expires after 24 hours. Download the image before it expires.

Send requests with cURL

Prerequisites

Before you begin, make sure you have:

A Model Studio API key
cURL installed on your system
Exported API key as $DASHSCOPE_API_KEY

Check if cURL is installed

To check whether cURL is installed, run:

curl --version

Expected output:

curl 8.x.x (x86_64-apple-darwin23.0) libcurl/8.x.x ...

If you see command not found (Linux/macOS) or 'curl' is not recognized (Windows), download and install cURL.

Step 1: Create a task

Run the following command in your terminal:

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis \
    -H 'X-DashScope-Async: enable' \
    -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
    -H 'Content-Type: application/json' \
    -d '{
    "model": "wan2.5-t2i-preview",
    "input": {
        "prompt": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"
    },
    "parameters": {
        "size": "1024*1024",
        "n": 1
    }
}'

Different regions use separate base_urls.

The response returns a task_id:

cURL response with task_id

Step 2: Poll for the result

Replace {task_id} with the value from Step 1:

curl -X GET https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"

Different regions use separate base_urls.

When task_status is SUCCEEDED, the response contains the image URL:

Next steps

Explore API parameters: See the text-to-image API reference for all input and output parameters.
Generate videos: Use the first-frame-to-video API.
Browse available models: Visit the Model list for all image and video models.