Qwen Image 3.0 Pro
Model ID qwen-image-3.0-pro/text-to-image
Overview
Image generation with automatic prompt rewriting and prompt-guided output dimensions.
Important: Output URLs are valid for about 24 hours; download promptly.
Endpoint
POST /v1/images/generations/async
Authentication
Authorization: Bearer <AIAPIAIAPI_API_KEY>
Request Body
| Parameter | Type | Required | Nullable | Default | Constraints | Description |
|---|---|---|---|---|---|---|
model | string | Yes | No | - | values: qwen-image-3.0-pro/text-to-image | Model ID used to route the request. |
prompt | string | Yes | No | - | - | Text prompt describing the desired output. |
negative_prompt | string | No | No | - | - | Content to exclude from the output. |
size | string | No | No | - | - | WIDTHxHEIGHT; each edge must be 512–2048 pixels. Omit to select dimensions automatically. |
seed | integer | No | No | - | range: 0-2147483647 | Seed for reproducible generation; omit for a random seed. |
prompt_extend | boolean | No | No | `true` | - | Whether the upstream model should expand or enhance the prompt. |
prompt_extend_mode | string | No | No | `direct` | values: direct, agent | Prompt rewriting strategy: direct for a single pass, agent for an agentic rewrite pipeline. |
n | integer | No | No | `1` | range: 1-4 | Number of images generated by one task. |
model
Type: string · Required: Yes · Nullable: No
Model ID used to route the request.
prompt
Type: string · Required: Yes · Nullable: No
Text prompt describing the desired output.
negative_prompt
Type: string · Required: No · Nullable: No
Content to exclude from the output.
size
Type: string · Required: No · Nullable: No
WIDTHxHEIGHT; each edge must be 512–2048 pixels. Omit to select dimensions automatically.
seed
Type: integer · Required: No · Nullable: No
Seed for reproducible generation; omit for a random seed.
prompt_extend
Type: boolean · Required: No · Nullable: No
Whether the upstream model should expand or enhance the prompt.
prompt_extend_mode
Type: string · Required: No · Nullable: No
Prompt rewriting strategy: direct for a single pass, agent for an agentic rewrite pipeline.
n
Type: integer · Required: No · Nullable: No
Number of images generated by one task.
Request Example
curl --request POST \
--url https://aiapiaiapi.com/v1/images/generations/async \
--header 'Authorization: Bearer $AIAPIAIAPI_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"model": "qwen-image-3.0-pro/text-to-image",
"prompt": "A cinematic camera movement through a forest",
"prompt_extend": true
}'JSON
{
"model": "qwen-image-3.0-pro/text-to-image",
"prompt": "A cinematic camera movement through a forest",
"prompt_extend": true
}Response
{
"code": "success",
"message": "",
"data": { "task_id": "image_01K2ABC123" }
}Task Status
Use the task_id from the create response:
GET /v1/images/generations/async/{task_id}
{
"code": "success",
"message": "",
"data": {
"task_id": "image_01K2ABC123",
"status": "SUCCESS",
"progress": "100%",
"outputs": ["https://cdn.example.com/images/image_01K2ABC123.png"],
"start_time": 1786960805,
"finish_time": 1786960900,
"submit_time": 1786960800,
"fail_reason": ""
}
}Error Responses
Validation errors return HTTP 400 with a stable error code.
{
"code": "unsupported_parameter",
"message": "The parameter is not supported by this model.",
"data": null
}Documentation Index
Fetch the complete documentation index at:
https://aiapiaiapi.com/llms.txt
Use this file to discover all available API documentation.