Skip to main content
POST

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
enum<string>
required

Required. It is recommended to use the public model ID bailian/qwen-image-3.0-pro; the short model name without the vendor prefix is ​​only available if the account alias is configured.

Available options:
bailian/qwen-image-3.0-pro,
qwen-image-3.0-pro
prompt
string
required

Required. Image generation or editing instructions support Chinese and English. The official recommendation is no more than about 4,500 tokens.

Minimum string length: 1
size
string
default:1024x1024

Optional. Output size in the format WIDTHxHEIGHT, for example 1024x1024. When auto is omitted or passed, the gateway sends 1024x1024 to the upstream; the official pixel area range is 512×512 to 2048×2048, and the aspect ratio is 1:8~8:1.

Pattern: ^(auto|[1-9]\d*x[1-9]\d*)$
Examples:

"1024x1024"

"2048x2048"

"1536x1024"

images
object[]

Optional. Drawing/editing reference pictures, up to 3 pictures. Each item provides a file_id or image_url; when omitted, a Vincentian image.

Required array length: 1 - 3 elements
prompt_extend
boolean
default:true

Optional. Whether to enable intelligent prompt word rewriting.

prompt_extend_mode
enum<string>
default:direct

Optional. Prompt word rewriting mode. Direct supports Vincentian diagrams and Tusheng diagrams; agent only supports Vincentian diagrams.

Available options:
direct,
agent
enable_thinking
boolean
default:true

Optional. Whether to enable thinking mode. When set to true prompt_extend cannot be turned off explicitly.

negative_prompt
string

Optional. Describe what you don't want to appear in the results.

seed
integer

Optional. Random seed. Fixed seeds improve result reproducibility but do not guarantee pixel-level consistency.

Required range: 0 <= x <= 2147483647
watermark
boolean
default:false

Optional. Whether to add Qwen-Image watermark in the lower right corner of the generated image.

response_format
enum<string>
default:b64_json

Fixed returning Base64 image so that the response conforms to the Response Schema of this interface.

Available options:
b64_json,
url

Response

200 - application/json

The image was generated successfully. The gateway has downloaded the upstream temporary image and converted it to Base64 without the data URL prefix.

created
integer<int64>
required

The Unix timestamp (in seconds) when the gateway completed response conversion.

Required range: x >= 0
background
string
required

The current Qwen path is fixed to return opaque.

Allowed value: "opaque"
data
object[]
required

Generate a list of results.

Minimum array length: 1
output_format
enum<string>

The format inferred by the gateway based on the Content-Type of the downloaded image. Omitted when no recognized type is provided by the upstream.

Available options:
png,
jpeg,
webp
size
string

Actual or requested output size. Omitted when neither the request nor the upstream response provides a size.

Pattern: ^[1-9][0-9]*x[1-9][0-9]*$