OCRRouter

OCRmyPDF vs Florence-2

Pick OCRmyPDF to make scanned PDF archives searchable and keep them as PDF/A. Pick Florence-2 when you need text with bounding boxes from short English labels or scene text, or when the same model must also do detection. Neither gives you Markdown, tables or reliable handwriting.

OCRmyPDFocrmypdf/ocrmypdfFlorence-2microsoft/florence-2
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.0 s / page0.8 s / page
Best forSearchable PDFs from scansLightweight OCR with boxes
InputsPDF, imagesimages
Languages100+ languages (via Tesseract)English
Max pages per request1,000500
TablesNoNo
HandwritingNoNo
MathNoNo
Bounding boxesNo✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ YesNo
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

  • It outputs validated searchable PDF/A by default, which suits archiving and compliance workflows.
  • It adds the OCR layer losslessly where possible, without re-encoding other page content.
  • It covers 100+ languages through Tesseract language packs and runs on CPU only, spread across all cores.

Choose Florence-2 if

  • It returns quadrilateral boxes per text line with OCR_WITH_REGION, which a PDF text-layer tool does not give you.
  • It is small at 0.23B (base) or 0.77B (large) parameters and MIT licensed, so it suits lightweight edge OCR in English.
  • The same model also does captioning, detection and grounding, so one model can serve a mixed pipeline.

Key differences

OCRmyPDFFlorence-2
What it isCommand-line tool that adds a Tesseract text layer to scanned PDFsPrompt-based vision model with OCR and OCR with regions, plus captioning and detection
LicenceMPL-2.0MIT
How you run itLocal library/CLI, CPU only, parallel across all coresSelf-hosted via Transformers, 0.23B base or 0.77B large
OutputSearchable PDF/A and plain textPlain text and bounding boxes
Languages100+ via Tesseract language packsWeak on CJK: Chinese output mostly wrong because the vocabulary lacks CJK characters. Spelling errors and missing spaces seen on French text
HandwritingNot suited to handwritingSpelling errors and missing spaces on cursive handwriting in a Hugging Face blog test
Known failureFile size can double or quadruple with --deskew --clean-final; --skip-text with default PDF/A removes form fields; hangs on PDFs whose forms share one Resources dictionaryNo Markdown, tables or LaTeX; the continued-pretrained checkpoint used only 0.1B samples and might not be well trained

Sources

What each one is

OCRmyPDF

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

OCRmyPDF details

Florence-2

Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.

Florence-2 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": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

OCRmyPDF alternativesFlorence-2 alternativesBest OCR models in 2026