GLM-OCR Models by Zhipu AI
1 model
Last refreshed 2026-07-11. Next refresh: weekly.
Capabilities
VisionAll models
MultimodalAll models
Structured OutputsAll models
Links
WebsiteAbout
GLM-OCR is Zhipu AI's vision family for optical character recognition, document understanding, and layout-aware parsing through the BigModel API.
Decision facts
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
GLM-OCRCurrent
Use when the workload needs vision, structured outputs, and multimodal inputs.
Unknown releasevisionstructured outputsmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| GLM-OCR | Use when the workload needs vision, structured outputs, and multimodal inputs. | Unknown release | visionstructured outputsmultimodal inputs | Current |
Release Timeline
1 release groupUnknown release
1 current
GLM-OCR
Currentvisionstructured outputsmultimodal inputs
Specifications(1 models)
| Model | Released | Vision | Multimodal | Structured Outputs |
|---|---|---|---|---|
| GLM-OCR | — | Yes | Yes | Yes |
