DeepSeek-OCR alternatives
Models that cover what DeepSeek-OCR does, closest first. All of them take the same request, so trying one is a one-word change.
Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.
Small open-source OCR model from Z.ai with layout regions. MIT licensed.
Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
Datalab's OCR model that keeps layout and handles forms, tables and handwriting.
Single vision model from rednote that does layout detection and content recognition together.
Dashed tags are things DeepSeek-OCR does not support. Model IDs: paddle/paddleocr-vl, zai/glm-ocr, baidu/unlimited-ocr, opendatalab/mineru, datalab/chandra, rednote/dots-ocr.