AllenAI's olmOCR Converts PDFs and Images to Markdown for Under $200 Per Million Pages

AllenAI's open-source olmOCR toolkit converts PDFs and images into clean Markdown text — including equations, tables, and handwriting — for under $200 per million pages, with its latest v0.4.0 release scoring 82.4 on a 7,000+ test benchmark, rivaling top OCR tools while supporting GPU inference, Docker, and multi-node cloud processing.

• AllenAI's olmOCR is an open-source toolkit that converts PDFs, PNGs, and JPEGs into clean Markdown text, supporting equations, tables, handwriting, and complex layouts at a cost of under $200 per million pages.
• The latest release, v0.4.0, achieves a benchmark score of 82.4 on olmOCR-Bench — a 7,000+ test case evaluation suite — competing closely with top tools like Chandra OCR and PaddleOCR-VL.
• The toolkit supports local GPU inference, remote vLLM servers, Docker deployment, and multi-node AWS S3-based cluster processing, with verified compatibility across external providers like DeepInfra, Parasail, and Cirrascale.