GLM-OCR
Free online OCR for images and PDFs to text
About GLM-OCR
GLM-OCR is a free online optical character recognition tool that turns images, scanned documents and PDFs into editable text. It is aimed at students, researchers, office workers and developers who need to digitize paper archives, financial statements, contracts or technical documents without a paid desktop package.
Beyond plain text, the tool is built to recognize tables, mathematical formulas and code blocks, with formulas returned as LaTeX and output available as plain text, Markdown or structured JSON. The site describes a lightweight model with 0.9B parameters that supports several major languages and can run through a cloud API or be deployed locally with tools such as Ollama, vLLM or Docker.
The project is open source under the Apache-2.0 license, so teams can inspect the code and host it themselves. The browser tool offers a quick way to test documents before committing to an API integration.
Related tools
GLM-OCR alternatives
Ardor
One AI agent that builds, deploys and runs your apps
Reimorph
Edit photos from a reference image using text prompts
ImageToSTL
Turn a photo into a 3D-printable model with AI
BlaBlaScribe
AI transcription, subtitles and dubbing from audio or video
Token360
One OpenAI-compatible API for text, image, audio and video
Image to Prompt
Turn any image into a detailed AI image prompt