{"id":"olmocr","name":"olmOCR","maker":"Allen Institute for AI","url":"https://olmocr.allenai.org","repo":"allenai/olmocr","package":"pypi:olmocr","summary":"An open toolkit and model for converting PDFs and images into clean text, built to run at large scale.","details":"It uses a fine-tuned vision-language model and a pipeline that can process many pages on GPUs. It is a Python package and is Apache licensed. The project releases model weights, a training data set and a toolkit that renders pages to images before reading them.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/olmocr","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}