OCRRouter

OCRmyPDF vs Unstructured

Pick OCRmyPDF to make scanned PDF archives searchable and keep them as PDF/A. Pick Unstructured to ingest mixed file types (PDF, HTML, Word, PowerPoint, email, images) into typed elements for RAG. They do different jobs: OCRmyPDF returns a PDF with a text layer, Unstructured returns structured JSON.

OCRmyPDFocrmypdf/ocrmypdfUnstructuredunstructured/unstructured
TypeOpen sourceOCR API
Price1 credit / page20 credits / page
Per 1,000 pages$1.00$20.00
Typical speed1.0 s / page3.0 s / page
Best forSearchable PDFs from scansMixed file types into RAG
InputsPDF, imagesPDF, images, DOCX
Languages100+ languages (via Tesseract)Multilingual
Max pages per request1,0001,000
TablesNo✓ Yes
HandwritingNoNo
MathNoNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
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 OCRmyPDF if

  • You need validated searchable PDF/A output for archiving or compliance.
  • You want the OCR layer added losslessly without re-encoding other page content, running on CPU only across all cores.
  • You need Tesseract's 100+ languages through language packs, with no hosted service or per-page fee.

Choose Unstructured if

  • You ingest PDFs, HTML, Word, PowerPoint, emails and images through one library.
  • You need JSON elements with bounding boxes rather than a PDF with a text layer.
  • You want to start on the hosted platform with 10,000 free pages, then pay $0.015 per page.

Key differences

OCRmyPDFUnstructured
LicenceMPL-2.0Apache-2.0 for the open-source library; proprietary for the hosted platform
How you run itLocal command-line tool, CPU onlySelf-hosted Python library or hosted API
PriceFree, self-hosted (you pay for compute)Library is free. Hosted: first 10,000 pages free, then $0.015 per page. Business is custom.
OutputSearchable PDF/A and plain textJSON, HTML, plain text and bounding boxes
TablesNo table, layout or Markdown outputVendor benchmark of table cell content: 0.426 open-source vs 0.866 hosted
Input typesScanned PDFsPDFs, HTML, Word, PowerPoint, emails and images
Known failure--skip-text with default PDF/A output removes form fields (issue #1790). Hangs on PDFs whose forms share one Resources dictionary (issue #1763).hi_res tables cut off at edges and drop first letters (issue #3262). Table OCR ignores language settings (issue #1694).

Sources

What each one is

OCRmyPDF

Command-line tool that adds a searchable text layer to scanned PDFs, using Tesseract.

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

Questions

More comparisons

OCRmyPDF alternativesUnstructured alternativesBest OCR models in 2026