alibaba/qwen-image-3
Qwen Image 3 by Alibaba - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runalibaba/qwen-image-3Input Schema
4 parameters · 1 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Text prompt describing the desired image. Supports Chinese and English. Max 800 characters. · Min length: 1 · Max length: 800 |
seed | integer | Optional | Random seed for reproducibility (0-2147483647). |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16 |
output_format | string | Optional | The format of the generated image. · Options: jpeg, png · Default: "png" jpegpng |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "alibaba/qwen-image-3",
"prompt": "A cute baby koala holding a card that says \"Qwen Image 3 is now available on fal\" while on a water slide",
"output_format": "png"
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Qwen Image 3
Qwen Image 3 is the SandBase text-to-image route backed by the qwen-image-3.0-pro generation model. It is designed for visually dense compositions where layout, small text, multilingual typography, and photographic detail all need to survive the move from a written brief to a finished image.
The endpoint accepts Chinese or English prompts up to 800 characters and produces one image per request. Ten preset aspect ratios cover ultrawide, landscape, square, portrait, and vertical delivery, while an optional seed supports repeatable creative iteration.
Highlights
- Complex layout generation. Compose information-heavy designs such as newspapers, storyboards, menus, and exam-paper-style pages instead of limiting prompts to a single isolated subject.
- Small-text rendering. Preserve fine typographic detail down to approximately 10-pixel text when the prompt calls for dense labels, captions, or interface-like content.
- Multilingual typography. Render multilingual fonts for creative work that combines Chinese, English, or other written content with the visual composition.
- Photographic-level detail. Generate polished scenes with fine material, lighting, and surface detail for editorial, advertising, and product-oriented imagery.
Pricing
| Unit | Base price |
|---|---|
| Per request | $0.042 |
When to Use
| Use case | Why this model fits |
|---|---|
| Newspapers, menus, and structured posters | The model is designed to organize multiple visual and textual regions in a complex layout. |
| Storyboards and instructional sheets | Combine panels, captions, and scene direction in one composition. |
| Multilingual campaign artwork | Place Chinese, English, or mixed-language typography directly in the creative brief. |
| Text-rich social assets | Ask for small labels and dense copy while selecting a delivery-ready portrait or square ratio. |
| Detailed product and editorial imagery | Request photographic lighting, materials, and surface finish in a controlled composition. |
Prompt Guide
Write the prompt as a layout brief: name the document or scene type, divide the composition into regions, specify exact visible text, and then describe typography, imagery, lighting, palette, and finish. Put quoted copy exactly as it should appear and keep competing layout instructions to a minimum.
{
"prompt": "一张现代中文咖啡馆菜单海报，顶部标题精确写‘夏日特饮’，三栏网格分别展示冰椰拿铁、青柠气泡水和蜜桃乌龙，每栏包含清晰的小号中文品名与价格。奶油白背景，墨绿色无衬线字体，写实饮品摄影，柔和窗边光，整洁高级的编辑设计。",
"aspect_ratio": "4:5",
"output_format": "png",
"seed": 24680
}
Technical Specs
| Property | Details |
|---|---|
| Model ID | alibaba/qwen-image-3 |
| Required input | prompt |
| Optional inputs | aspect_ratio, output_format, seed |
| Prompt | Chinese or English; 1–800 characters |
| Aspect ratios | 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 |
| Output formats | png (default) or jpeg |
| Output | Downloadable image URL with optional content type |
| Execution | Asynchronous |
Related Models
alibaba/qwen-image-3/edit— edit existing imagery with the same Qwen Image generation family.alibaba/qwen-image-3/text-to-image— use the explicit text-to-image route in the same family.alibaba/qwen-image-edit/inpaint— target a masked region for inpainting.