10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 632 ms

1. 1GLM-OCR Document Readerdemo or tutorialno passport yet

   MCP serverrecord

   • glm_ocr_demo_run_ocr

     Read one document image with GLM-OCR. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: Rendered Markdown, raw model text, parsed JSON

2. 2lucataco/glm-ocrverified and signedpassport

   modelrecord

   • lucataco/glm-ocr

     Compact 0.9B multimodal OCR model from Z.ai. State-of-the-art on OmniDocBench V1.5 (94.62, #1 overall). Four modes: text recognition, formula (LaTeX), table parsing, and JSON-schema information extraction. Fits on a single T4.

3. 3GLM-OCRverified and signedpassport

   modelrecord1,700,675 downloads/month

   • image-to-text

     Task: image-to-text

4. 4GLM-OCR Demodemo or tutorialno passport yet

   MCP serverrecord

   • GLM_OCR_Demo_ocr

     Extract text, formulas, or tables from a document image using GLM-OCR. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

5. 5GLM-OCRfound in code, not yet checkedno passport yet
   • image-text-to-text

     Task: image-text-to-text

6. 6glm-ocr-mcpfound in code, not yet checkedno passport yet
   • ocr_pdf

     OCR PDF 文件并返回 Markdown（小文件直接调用；超大 PDF 建议用 start_pdf_ocr 异步执行）。

7. 7GLM OCR Demodemo or tutorialno passport yet

   MCP serverrecord

   • GLM_OCR_Demo_noop_1

   • GLM_OCR_Demo_noop

   • GLM_OCR_Demo_run_router

8. 8GLM OCR MCP Serverfound in code, not yet checkedno passport yet

   MCP servercs-qyzhang/glm-ocr-mcp

   • extract_text

     Extract text from local files or URLs. Supported formats: PNG, JPG/JPEG, PDF.