OCRRouter

MonkeyOCR vs Unstructured

Pick MonkeyOCR for English and Simplified Chinese PDFs such as academic papers with formulas and tables, but only for research or evaluation, since its v1 weights cannot be used commercially without a written license. Pick Unstructured for ingesting mixed file types (PDF, Word, PowerPoint, email, HTML, images) into a RAG pipeline, with a commercially usable Apache-2.0 library or a hosted API.

MonkeyOCRmonkeyocr/monkeyocrUnstructuredunstructured/unstructured
TypeOpen sourceOCR API
Price2 credits / page20 credits / page
Per 1,000 pages$2.00$20.00
Typical speed1.5 s / page3.0 s / page
Best forChinese and English PDFsMixed file types into RAG
InputsPDF, imagesPDF, images, DOCX
LanguagesChinese, EnglishMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
MultilingualNo✓ 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 MonkeyOCR if

  • Its authors report an OmniDocBench overall edit distance of 0.138 (EN) and 0.206 (ZH) for pro-3B, the best among the models they compared.
  • It runs self-hosted on an 8GB RTX 4060 with quantized weights, and outputs Markdown, JSON, LaTeX, HTML and bounding boxes.
  • Pro-1.2B is about 36% faster than pro-3B for about 1.6% lower accuracy, which helps when throughput matters.

Choose Unstructured if

  • It handles PDFs, HTML, Word, PowerPoint, emails and images in one library, with many connectors.
  • The library is Apache-2.0, and the hosted platform gives 10,000 free pages, then $0.015 per page.
  • Strategies Auto, Fast, High-Res and VLM let you trade speed for quality, and Fast suits born-digital PDFs.

Key differences

MonkeyOCRUnstructured
LicenceCode Apache-2.0; v1 weights research and non-commercial onlyApache-2.0 library; proprietary hosted platform
How you run itSelf-host only, via LMDeploy or DockerSelf-host the library or use the hosted API
PriceFree for research; commercial use needs a separate license from the authorsLibrary free; hosted first 10,000 pages free, then $0.015 per page
Input scopePDFs in English and Simplified Chinese; photos, handwriting, Traditional Chinese and other languages not fully supportedPDFs, HTML, Word, PowerPoint, emails and images
Output formatsMarkdown, JSON, LaTeX, HTML, bounding boxesJSON, HTML, plain text, bounding boxes
Table qualityPro-3B table TEDS 81.5 (EN) / 87.5 (ZH) on OmniDocBench, reported by the authorsVendor's own benchmark: table cell content 0.426 for the open-source library versus 0.866 hosted
Known failurePro-3B runs under 1 page/s (about 0.49 pages/s on a 3090); Docker on 20/30/40-series and V100 needs a patched imagehi_res tables cut off at edges and drop first letters; table OCR ignores language settings; telemetry is sent by default

Sources

What each one is

MonkeyOCR

Open-source document parser that splits work into structure, recognition and relation steps.

MonkeyOCR details

Unstructured

Document ETL for RAG. Partitions many file types into typed elements; open-source library too.

Unstructured 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": "monkeyocr/monkeyocr","fallbacks": ["unstructured/unstructured"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

MonkeyOCR alternativesUnstructured alternativesBest OCR models in 2026