← back to all tools
DOC · Documents & OCR

DeepSeek-OCR

A vision model that reads documents and compresses pages into very few tokens, making long PDFs cheap to feed a model.

view source ↗23k stars
ocr few tokens

license

MIT

language

Python

status

bookmarked

added

2026-06-17

categories

DOC · Documents & OCR

tags

building blockOCRvision

what we've heard

1 note from the team

tip
Alexander
For anyone dealing with OCR — optical context compression.