{"id":"dots-ocr","name":"dots.ocr","maker":"dots.ocr team","url":"https://github.com/studio-dots-ai/dots.ocr","repo":"studio-dots-ai/dots.ocr","summary":"A single vision-language model that parses document layout and reads text in many languages.","details":"It is run locally with Python and a GPU and outputs structure with positions. It is MIT licensed. The repository provides weights and inference code, and results include reading order for each page.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/dots-ocr","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T21:21:51.986Z","archived":false,"licence":"MIT","language":"Python","last_change":"2026-03-24T14:43:26.000Z","latest_release":null}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}