OCRRouter

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/mineruEasyOCRjaided/easyocr
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page0.9 s / page
Best forAcademic PDFsQuick scripts and scene text
InputsPDF, imagesimages
Languages80+ languages80+ languages
Max pages per request500100
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNo✓ Yes
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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

MinerUEasyOCR
What it isDocument parsing toolkit from OpenDataLab; runs as CLI, API or WebUIPython OCR library using CRAFT detection and a CRNN recognizer
OutputMarkdown, HTML, LaTeX, DOCX, EPUB, JSONPlain text and bounding boxes
LicenceMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0Apache-2.0
HardwareBasic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAMPyTorch on CPU (gpu=False) or NVIDIA GPU
BenchmarkolmOCR-Bench overall 75.2 (MinerU 2.5.4); ParseBench mean 45.9 (MinerU2.5)Not published
TablesVLM tiers drop merged header rows in tables such as bank statement account lines (issue #5554)Not suited to full-page layout or tables
Known failuresRepeated 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

What each one is

MinerU

Open-source PDF to Markdown pipeline popular for academic and Chinese documents.

MinerU details

EasyOCR

Python OCR library with a simple API. Returns text lines with boxes and confidence.

EasyOCR details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

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