MinerU vs PaddleOCR (PP-OCR)
Pick MinerU when you need whole documents turned into Markdown, HTML, LaTeX or DOCX, such as academic papers or mixed PDF and Office corpora for RAG. Pick PP-OCR when you need fast text detection and recognition under an Apache-2.0 licence, on CPU, edge devices or in the browser. The main split is scope: MinerU parses documents, PP-OCR returns text lines and boxes.
MinerUopendatalab/mineru | PaddleOCR (PP-OCR)paddle/paddleocr | |
|---|---|---|
| Type | Open source | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 2.0 s / page | 0.7 s / page |
| Best for | Academic PDFs | Fast printed text, Chinese and English |
| Inputs | PDF, images | PDF, images |
| Languages | 80+ languages | 80+ languages |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | No |
| Handwriting | No | No |
| Math | ✓ Yes | No |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | No | ✓ Yes |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
Which to choose
Choose MinerU if
- It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML in one tool and exports Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
- It targets Chinese and English academic papers and mixed Office and PDF corpora for RAG.
- Its basic ONNX tier runs on CPU with about 2 GB RAM, so you can start batch conversion without a GPU.
Choose PaddleOCR (PP-OCR) if
- It is Apache-2.0 licensed, with no extra conditions and no AGPL-tagged weights.
- PP-OCRv6 medium is 34.5M parameters, runs on CPU, NVIDIA GPU and Kunlunxin XPU, and has an official PaddleOCR.js browser SDK.
- One PP-OCRv6 model covers 50 languages, including Chinese, English, Japanese and 46 Latin-script languages.
Key differences
| MinerU | PaddleOCR (PP-OCR) | |
|---|---|---|
| What it does | Document parsing toolkit: PDFs, images and Office files to Markdown or JSON | Text detection and recognition pipeline; returns text lines and boxes |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Apache-2.0 |
| Model size | MinerU2.5 VLM: 1.2B parameters | PP-OCRv6 medium: 34.5M parameters |
| Hardware | Basic tier: CPU with 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | CPU, NVIDIA GPU, Kunlunxin XPU and other accelerators; 0.13s on A100 and 5.2x CPU speedup with OpenVINO, per the README |
| Output formats | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Plain text, bounding boxes, JSON |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published |
| Known failure | VLM tiers drop merged header rows in tables such as bank statements; VLM pipeline can repeat content, producing 300 KB figure blocks | Tables and formulas need the separate PP-Structure or VL pipelines; PP-OCRv6 weights contain denormals that make CPU inference 4 to 11x slower |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- PaddleOCR GitHub README
- PP-OCRv6 on Hugging Face
- RapidOCR issue #743 denormal weights
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsPaddleOCR (PP-OCR)
Baidu's classic open-source text detection and recognition pipeline. Light enough to run on CPU.
PaddleOCR (PP-OCR) detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "opendatalab/mineru","fallbacks": ["paddle/paddleocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesPaddleOCR (PP-OCR) alternativesBest OCR models in 2026