MinerU vs EasyOCR
Pick MinerU to convert full documents such as academic papers, bank-style tables and mixed PDF/Office files into Markdown or JSON. Pick EasyOCR to read short text, such as scene text in photos, with boxes in a few lines of Python. The main split is scope: MinerU parses whole documents, while EasyOCR returns text and bounding boxes only and is listed as unsuited to full-page layout or tables.
MinerUopendatalab/mineru | EasyOCRjaided/easyocr | |
|---|---|---|
| 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 | 0.9 s / page |
| Best for | Academic PDFs | Quick scripts and scene text |
| Inputs | PDF, images | images |
| Languages | 80+ languages | 80+ languages |
| Max pages per request | 500 | 100 |
| 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
- You need document-level output: Markdown, HTML, LaTeX, DOCX, EPUB or JSON from PDFs, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML.
- You are converting Chinese and English academic papers or mixed Office and PDF corpora for RAG.
- You have no GPU and can accept basic quality: the basic ONNX tier runs on CPU with 2 GB RAM.
Choose EasyOCR if
- You need text, boxes and confidence scores from photos or short snippets, in about three lines of Python.
- You need many scripts: 80+ languages including Latin, Chinese, Arabic, Devanagari and Cyrillic.
- You need a plain Apache-2.0 licence with no extra conditions or AGPL-tagged weights.
Key differences
| MinerU | EasyOCR | |
|---|---|---|
| What it is | Document parsing toolkit from OpenDataLab; runs as CLI, API or WebUI | Python OCR library using CRAFT detection and a CRNN recognizer |
| Output | Markdown, HTML, LaTeX, DOCX, EPUB, JSON | Plain text and bounding boxes |
| Licence | MinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0 | Apache-2.0 |
| Hardware | Basic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM | PyTorch on CPU (gpu=False) or NVIDIA GPU |
| Benchmark | olmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5) | Not published |
| Tables | VLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554) | Not suited to full-page layout or tables |
| Known failures | Repeated content producing 300 KB figure blocks (#5728); full-width Chinese punctuation converted to half-width (#5765) | No text after upgrading to 1.7.0 (#1039); gibberish when batch_size is above 1 (#1038); default reader fails on Apple M1 unless GPU is disabled (#1136) |
Sources
- MinerU GitHub README
- olmOCR-Bench table
- Issue #5554 table header rows
- EasyOCR GitHub README
- Issue #1039
- Issue #1038
What each one is
MinerU
Open-source PDF to Markdown pipeline popular for academic and Chinese documents.
MinerU detailsEasyOCR
Python OCR library with a simple API. Returns text lines with boxes and confidence.
EasyOCR 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": ["jaided/easyocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
MinerU alternativesEasyOCR alternativesBest OCR models in 2026