← back to all toolsDOC · Documents & OCRDeepSeek-OCRA 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 licenseMITlanguagePythonstatusbookmarkedadded2026-06-17categoriesDOC · Documents & OCRtagsbuilding blockOCRvisionLeave a review ↗what we've heard1 note from the teamAtipAlexanderFor anyone dealing with OCR — optical context compression.