GLM-Image
GLM-Image is Z.ai's text-to-image model, designed for complex instructions, knowledge-intensive scenes and text rendering.
Channel
Each channel is compared at its lowest input-price tier; output breaks ties. A dash means /api/pricing does not provide that rate. Selecting a channel updates the endpoints and call example below.
z-ai/glm-imagePrices and availability as published on Oct 12, 2026.
Capabilities
GLM-Image takes text as input and produces image as output. The model targets prompts that contain detailed instructions, knowledge-heavy subject matter and text that must appear in the picture.
Overview
GLM-Image is an image generation model from Z.ai that turns text prompts into images. Z.ai positions it as a flagship image model that is stronger on complex instructions and knowledge-intensive scenarios, with a focus on rendering text inside images. It combines an autoregressive model with a diffusion decoder.
It accepts text input and returns image output. It returns images in multiple resolutions. It was released on January 14, 2026. Its weights are openly available.
Pricing
GLM-Image is billed at $0.015 per image.
GLM-Image is available through RealRelay's OpenAI-compatible API.
Use cases
Use GLM-Image for graphics that must contain readable text, such as posters, banners and social cards, since text rendering is one of its documented strengths.
It also suits illustrations of knowledge-heavy topics, such as diagrams or educational visuals, where a detailed prompt describes many elements that the image has to get right.
Frequently asked questions
- What is GLM-Image?
- GLM-Image is Z.ai's text-to-image model, designed for complex instructions, knowledge-intensive scenes and text rendering.
- How much does GLM-Image cost?
- GLM-Image is billed at $0.015 per image.
- What inputs and outputs does GLM-Image support?
- GLM-Image accepts text input and returns image output.
- When was GLM-Image released?
- GLM-Image was released on January 14, 2026.
- How do I call GLM-Image via the API?
- Send requests to RealRelay's OpenAI-compatible API and use the model ID z-ai/glm-image.