olmOCR
AI2's open-source OCR — high-quality PDF-to-text at 1/32 the cost of GPT-4o API
AI2's open-source OCR tool for high-quality PDF-to-text conversion, at only 1/32 the cost of the GPT-4o API.
Translate documents, parse PDFs, and extract text with OCR.
Key features
- Converts PDFs and image documents into clean readable plain text
- Handles equations, tables, handwriting and complex formatting
- Removes headers and footers; preserves natural reading order
- Ships olmOCR-Bench with 7000+ test cases across 1400 documents
Good for
- Teams digitizing PDFs at scale for under $200 per million pages
- Researchers benchmarking OCR systems on complex documents
Stack & tags
vLLMDockerocrpdf-parsingdocument-aibenchmarkopen-weightsvlm
Similar open-source projects
微软 MarkItDown
★ 187,737Microsoft's open-source Python tool — convert PDF/Word/PPT/audio/YouTube to clean Markdown
DeepSeek-OCR
★ 23,926DeepSeek's novel OCR document model — "contextual optical compression"