v1

latestOpenAPI 3.0.1Z.AI Developer Agreement and Policy2026-07-131458163.2 KB

Generate Image (Async)

Use the GLM-Image series models to generate high-quality images from text prompts. Through quick and accurate understanding of user text descriptions, AI image expression becomes more precise and personalized. Only supports GLM-Image model.

post/paas/v4/async/images/generations

Request body

model'glm-image' required

Model code

promptstring required

The text description of the image to be generated.

quality'hd'

The quality of the generated image. hd: Generates a more detailed and rich image with higher overall consistency, takes about 20 seconds.

sizestring

Image size, recommended enum values: 1280x1280 (default), 1568x1056, 1056x1568, 1472x1088, 1088x1472, 1728x960, 960x1728. Custom parameter: Both width and height must be between 1024px-2048px, and must be divisible by 32, and the maximum pixel count must not exceed 2^22px.

user_idstring

Unique ID of the end user, helping the platform intervene in illegal activities, inappropriate content generation, or other abuses. ID length: 6 to 128 characters.

Example request

{
  "model": "glm-image",
  "prompt": "A cute little kitten.",
  "size": "1280x1280"
}

Response

Processing successful

modelstring

Model name used in this call.

idstring

Task order number generated by the platform, use this order number when calling the async result interface.

request_idstring

Task number submitted by the user during the client request or generated by the platform.

task_statusstring

Processing status, PROCESSING (processing), SUCCESS (success), FAIL (failure). Results need to be obtained via query.