GLM-OCR · jiekou

GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, achieving SOTA performance with a score of 94.62 on OmniDocBench V1.5. Optimized for real-world business scenarios, it delivers high-precision recognition for handwritten text, stamps, and code documentation. The model supports directly rendering complex tables into HTML code and extracting structured data from IDs and receipts into standard JSON format, enabling high-accuracy document parsing with minimal resource consumption.

Base modelAll models on this baseAll models of the providerto the provider

Read also: GLM API pricing: GLM-5.3, GLM-5.3 Flash and GLM-5.2 at every provider

All Zhipu GLM models at every provider

Input, $/1M $0.03

Output, $/1M $0.03

Context 32 000

Max output 32 000

Accepts images, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page