glm-image

Image
Text Rendering

Standard & Paid Price

The locked value is the exact Paid Price after your first top-up; the discount is derived from the two absolute prices
Unlock with a top-up
MeterStandard PricePaid PriceSave
Model price$0.015 / request$0.01425 / request-5%
Billing details

Description

Zhipu GLM-Image — image generation built on a hybrid autoregressive-understanding plus diffusion-decoding architecture, the first SOTA multimodal model trained end-to-end on Chinese-made chips (Huawei Ascend). Reads instructions rather than keywords and fills in detail the prompt leaves implicit, with markedly stronger text rendering (Chinese characters in particular) and knowledge-intensive scenes. One image per request.

Capabilities

Tasks
text-to-image

API endpoints

  • POST /v1/images/generations (image-generation)
  • POST /v1/chat/completions (openai)