πŸŽ‰ Get Free $5 on Signup！
Models
Enterprise
Subscribe
Resource
Activity
Documentation
Console

/alibaba/qwen-image-3.0

Q

Alibaba: Qwen Image 3

Qwen-Image-3.0 is Alibaba Cloud's image generation and editing model designed for efficient everyday visual creation. It supports text-to-image generation and image-to-image editing with up to three reference images, strong prompt understanding, reliable multilingual text rendering, and complex visual layout generation.

Modetext、image β†’ image
Input price$0.024754 per M tokens
Output priceβ€”
Context length
Listed at2026-08-04T00:00:00Z

Alibaba

Latencyβ€”
Throughputβ€”
Upload rateβ€”
Context lengthβ€”
Max outputβ€”
Input price$0.024754per request
Output priceβ€”per request
Cache readβ€”per request
Cache writeβ€”per request

Performance

Avg TPSβ€”
Avg latencyβ€”
Avg success rateβ€”
TPSβ€”
TTFTβ€”
Latencyβ€”
Success rateβ€”

Success rate

Speed

Code Example

curl ${API_BASE_URL}/v1/images/generations \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-3.0",
    "prompt": "Describe the image you want"
  }'

Replace <YOUR_API_KEY> with the API key generated on your token management page.

Authentication

All requests must include the Authorization: Bearer <TOKEN> header.

Endpoint Path

POST
images

Supported Parameters

ParameterTypeDefaultDescription
stringautoOutput image resolution. Use auto to let the model automatically select an appropriate resolution.
integer1Number of images to generate. Supported values: 1 to 6.
string-Describes visual elements or content that should not appear in the generated image.
integer-Random seed used for image generation. Supported range: 0 to 2147483647.
booleantrueWhether to enable intelligent prompt enhancement to improve generation quality.
booleantrueWhether to enable reasoning mode for improved image generation quality. Enabling it may increase generation time.
booleanfalseWhether to add a watermark to the generated image.

Rate Limits

GroupRPMTPMRPD

RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.

Pricing

ProviderBilling typePrice summary
Q
Qwen
Per call
Input price$0.024754per request
Completion price$β€”per request
Cache read price$β€”per request
Cache write price$β€”per request