GLM
Vision
OCR

Self-hosted OCR powered by zai-org/GLM-OCR — a 0.9B vision-language model ranking #1 on OmniDocBench V1.5. Handles plain text, tables, math formulas, and structured document parsing.

0Processed

0Words

—Avg Latency

01 Upload Image

🖼

Drag & drop an image PNG · JPG · WEBP · BMP · TIFF · Max 20 MB

Clear image

02 Extracted Text

📄

Upload an image and click
"Run GLM-OCR" to begin.

Initialising…

Model: — Device: — Uptime: — Errors: —

GLMVisionOCR

GLM
Vision
OCR