GLM-OCR — OCR AI Model

GLM-OCR reads a document image back as markdown with tables, formulas, code blocks and seals intact, not a flat wall of text. Multi-language, light on GPU, ten to forty seconds; handwriting suits DeepSeek OCR better.

Try in Studio

Details

  • CategoryOCR
  • Year2026
  • LicenseMIT

Compliance & Provenance

  • ProviderOpen-source (Zhipu) · Specialized
  • EU AI Act RiskMinimal Risk
  • Art. 50 TransparencyNot applicable

Inputs & Outputs

  • ImageInput · image
  • ImageOutput · image

    Detected texts as an image

  • TextOutput · string

    Detected texts as markdown

Tags

  • ocr
  • text-recognition
  • layout-analysis
  • document
  • table-recognition
  • formula-recognition
  • multi-language
  • gpu-heavy

Alternatives in Text Recognition(OCR)

Resources