OCRRouter

Docling vs OCRmyPDF

Pick Docling when you need structured output (Markdown, HTML or lossless JSON with layout and tables) from born-digital PDFs and Office files, for example RAG ingestion. Pick OCRmyPDF when you have scanned PDFs and need a searchable PDF/A archive. The main split is output: Docling gives structured documents, OCRmyPDF gives the same PDF with a text layer added.

Doclingibm/doclingOCRmyPDFocrmypdf/ocrmypdf
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.2 s / page1.0 s / page
Best forStructured export for RAGSearchable PDFs from scans
InputsPDF, images, DOCXPDF, images
LanguagesLatin scripts, CJK100+ languages (via Tesseract)
Max pages per request5001,000
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
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 Docling if

  • It reads PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL through one API.
  • Its lossless JSON export keeps layout, reading order and table structure, and it also writes Markdown, HTML, DocTags and plain text.
  • You can plug in OCR engines (EasyOCR, Tesseract, RapidOCR) or the 258M GraniteDocling VLM.

Choose OCRmyPDF if

  • It produces validated searchable PDF/A by default, which suits archives and compliance workflows.
  • It adds the OCR layer losslessly where possible, without re-encoding other content in the PDF.
  • It uses Tesseract, so it covers 100+ languages through language packs, and it spreads work across all CPU cores.

Key differences

DoclingOCRmyPDF
What it doesConverts PDFs, Office files, HTML and images into a structured DoclingDocumentAdds a Tesseract text layer to scanned PDFs
Output formatsMarkdown, HTML, JSON, DocTags, plain textSearchable PDF (PDF/A), plain text
Input formatsPDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRLScanned PDFs
OCR enginePluggable: EasyOCR, Tesseract, RapidOCR, or VLMs like GraniteDocling. Scan accuracy depends on the engine you choose.Tesseract only. Accuracy is capped by Tesseract.
LicenceMIT (individual models have their own licences)MPL-2.0
HardwaremacOS, Linux and Windows on x86_64 and arm64. CPU works, GPU speeds up model stages.CPU only, uses all cores
Known failureVersion 2.143.1 drops words and numbers with full-page Tesseract OCR (issue #5254). Reading order can merge neighbouring columns (issue #5132).--deskew --clean-final can double or quadruple file size (issue #948). --skip-text with default PDF/A output removes form fields (issue #1790).

Sources

What each one is

Docling

IBM's open-source document converter with a structured document model.

Docling details

OCRmyPDF

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

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

Questions

More comparisons

Docling alternativesOCRmyPDF alternativesBest OCR models in 2026