Qwen Image 3.0 Pro API Integration
Use Qwen Image 3.0 Pro through Rivya Public API v1 with model id qwen-image-3-pro, supported inputs, parameters, Files API rules, credits, and response examples.
qwen-image-3-pro
text, file
Required for reference modes
per_output_plus_input_image · 1K=6.4 · 2K=12 · input_image=0.5 · ⌈total⌉
Image
FIXED
800 characters
Request contract
Send the model id at the top level. Model-specific controls belong in params.
| Key | Type | Required | Default | Description |
|---|---|---|---|---|
| model | string | Yes | qwen-image-3-pro | Use the qwen-image-3-pro API model id. |
| prompt | string | Yes | - | Maximum 800 characters for this model. |
| params | object | Yes | - | Model-specific parameter object. Use the rows below for allowed keys. |
| client_request_id | string | No | - | Optional client-side id for tracing requests in your system. |
Model parameters
| Key | Type | Required | Default | Range | Options | Description |
|---|---|---|---|---|---|---|
| resolution | select | Yes | 1K | - | 1K, 2K | Resolution |
| image_size | select | No | 16:9 | - | 1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9 | Image size |
| output_format | select | No | png | - | png, jpeg | Output format |
| prompt_extend | select | No | true | - | true, false | Let the model rewrite a simple positive prompt before generation, or turn it off for tighter wording control. |
| nsfw_checker | select | No | false | - | false, true | Enable the model's optional content filter. No automated filter can guarantee complete coverage. |
| negative_prompt | text | No | - | - | - | Negative prompt |
| seed | number | No | 1 | min 0 / max 2147483647 / step 1 | - | Leave it empty for a new random result each time. Reusing the same integer makes it easier to reproduce or fine-tune a previous result. It stays closer only when the prompt and other key settings also remain similar, and it is not a guaranteed 1:1 match. |
Upload policy
Upload reference files first, then place the returned URL and duration token inside params.referenceMediaItems.
Reference images: Upload up to three JPEG, PNG, WebP, BMP, GIF, or TIFF images, no more than 10 MB each.
3
image
Video and audio references should carry durationToken from /api/v1/files when duration verification is required.
| kind | Max size | MIME types |
|---|---|---|
| image | 10 MB | image/jpeg, image/png, image/webp, image/bmp, image/gif, image/tiff |
Minimal request
{
"model": "qwen-image-3-pro",
"prompt": "A clean editorial product image on a soft studio background",
"params": {
"resolution": "1K",
"image_size": "16:9",
"output_format": "png",
"prompt_extend": "true",
"nsfw_checker": "false",
"negative_prompt": "Optional elements or failure modes to avoid, up to 5,000 characters.",
"seed": 1
}
}Reference-file request
{
"model": "qwen-image-3-pro",
"prompt": "A clean editorial product image on a soft studio background",
"params": {
"resolution": "1K",
"image_size": "16:9",
"output_format": "png",
"prompt_extend": "true",
"nsfw_checker": "false",
"negative_prompt": "Optional elements or failure modes to avoid, up to 5,000 characters.",
"seed": 1,
"referenceMediaItems": [
{
"url": "https://cdn.example.com/reference-image.png",
"kind": "image",
"name": "reference-image.png",
"mimeType": "image/png",
"width": 1024,
"height": 1024,
"sizeBytes": 1048576,
"imageDimensionsToken": "image_dimensions_token_from_original_files_api_upload_response"
}
]
}
}Create response
The create endpoint returns a public task id. Poll the status endpoint until the task succeeds or fails.
{
"id": "task_qwen_image_3_pro_example",
"status": "queued",
"model": "qwen-image-3-pro",
"reserved_credits": 7,
"final_credits": 0,
"settlement_status": "RESERVED",
"created_at": "2026-05-11T00:00:00.000Z",
"updated_at": "2026-05-11T00:00:00.000Z",
"result": null,
"error": null
}Common errors
validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found
Some modes require Files API reference uploads.