{"id":"deepseek-ocr","name":"DeepSeek-OCR","maker":"DeepSeek","url":"https://github.com/deepseek-ai/DeepSeek-OCR","repo":"deepseek-ai/DeepSeek-OCR","summary":"An open vision-language model for reading documents, which compresses page images into few tokens before decoding text.","details":"The repository gives code to run it with common inference servers on GPUs. It is MIT licensed. It targets page images and returns text, and the maker also released a second version in a separate repository.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"documents","category_name":"Document parsing and extraction","page":"https://modelmoot.com/tools/deepseek-ocr","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-15T20:20:00.691Z","archived":false,"licence":"MIT","language":"Python","last_change":"2026-01-27T03:45:14.000Z","latest_release":null}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}