Model Details
Released
Jan 14, 2026
Modalities
Text
Image
→
Image
Capabilities
Open weights
Where is GLM Image a perfect fit?
GLM-Image combines a 9B autoregressive generator with a 7B diffusion decoder, delivering strong semantic understanding, accurate text rendering, image editing, style transfer, and high-resolution generation. It can be a perfect fit for below use cases:
- Text-heavy posters, advertisements and banners
- Infographics and diagrams
- Presentation/slide graphics
- Product packaging and marketing creatives
- Chinese-language visual content
- Knowledge-intensive illustrations
- Image editing and background replacement
- Style transfer
- Identity-preserving generation
- Multi-subject image consistency
Its strongest differentiator is rendering meaningful, correctly spelled text inside generated images, rather than purely aesthetic image generation.
- Text-heavy posters, advertisements and banners
- Infographics and diagrams
- Presentation/slide graphics
- Product packaging and marketing creatives
- Chinese-language visual content
- Knowledge-intensive illustrations
- Image editing and background replacement
- Style transfer
- Identity-preserving generation
- Multi-subject image consistency
Its strongest differentiator is rendering meaningful, correctly spelled text inside generated images, rather than purely aesthetic image generation.
Quick Model Estimate
Your GLM Image Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000)
—
📤 Output (1000 × $0.015000)
—
Cost Breakdown
📥 Input
📤 Output
Prices are watched for changes and checked against the provider's own page.
Pricing
FAQs about GLM Image
What input types does GLM Image support?
GLM Image accepts text and image input, and returns image.