1–3 ordered references for editing, 10 MB each. Recommended dimensions: 384–3,072 pixels per side; this recommendation is not a hard bound. Public URL or Base64; GIF uses the first frame.Source for Input image limits (opens in a new tab)
Resolution controls
Generation defaults to 2048×2048. Editing defaults near 1024×1024 pixel area and follows the last reference aspect ratio; specified dimensions round to nearby multiples of 16.Source for Resolution controls (opens in a new tab)
Reviewed access uses synchronous DashScope multimodal-generation for text-to-image and image editing. A generic async section on the generation page has a different schema and unresolved version scope.Source for Request mode (opens in a new tab)
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation (synchronous). Match workspace, API key and region. Deployment scope: International.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Image generation
Successful output image1
$0.075
image
Rate conditions
Only successful generated images are billed; image input is free because no input tariff is published. Native USD rate; International. No text-token or per-question estimate.
POST https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation (synchronous). Match workspace, API key and region. Deployment scope: Global.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Image generation
Successful output image1
$0.071676
image
Rate conditions
Only successful generated images are billed; image input is free because no input tariff is published. Native USD rate; Global. No text-token or per-question estimate.
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Classification inference: the separately documented Qwen Image 2.0/3.0 API selector has no exact checkpoint in the reviewed official Qwen image-weight inventory. Public Qwen-Image, Edit, Layered and 2.1 checkpoints are excluded; private lineage and parameter counts are not inferred from them.
