MinerU alternatives
Models that cover what MinerU does, closest first. All of them take the same request, so trying one is a one-word change.
Open-source vision model that compresses pages into few tokens.
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.
Fast document OCR that returns clean Markdown with tables and embedded images.
Document parser built for RAG pipelines, with several quality tiers.
Dashed tags are things MinerU does not support. Model IDs: deepseek/deepseek-ocr, paddle/paddleocr-vl, zai/glm-ocr, baidu/unlimited-ocr, mistral/mistral-ocr, llamaindex/llamaparse.