OCRRouter

Jina OCR vs OCRmyPDF

Pick Jina OCR when you need page-to-Markdown, HTML or LaTeX output for non-commercial work or research, and you have a GPU. Pick OCRmyPDF when you need to turn scanned PDFs into searchable PDF/A on CPU, for archives or office scanner pipelines. The main split is output: Jina OCR returns structured text, OCRmyPDF keeps the original PDF and adds a text layer.

Jina OCRjina/jina-ocrOCRmyPDFocrmypdf/ocrmypdf
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed1.5 s / page1.0 s / page
Best forClean Markdown at low costSearchable PDFs from scans
InputsPDF, imagesPDF, images
LanguagesAbout 100 languages100+ languages (via Tesseract)
Max pages per request2001,000
Tables✓ YesNo
HandwritingNoNo
Math✓ YesNo
Bounding boxesNoNo
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 Jina OCR if

  • It outputs Markdown, HTML and LaTeX, so you get document structure that OCRmyPDF does not produce.
  • It scores 91.14 on OmniDocBench v1.6 (reported by the authors) and 83.4 on olmOCR-Bench, 7.4 points above DeepSeek-OCR.
  • It has only about 570M active parameters (3B MoE) and runs at 2.57 pages per second on an A100, and you can self-host it or use Jina's hosted API.

Choose OCRmyPDF if

  • It produces validated searchable PDF/A by default, which suits archiving and compliance workflows.
  • It runs on CPU only and spreads work across all cores, so you need no GPU.
  • It is MPL-2.0 and free to self-host, with no non-commercial restriction, and Tesseract language packs cover 100+ languages.

Key differences

Jina OCROCRmyPDF
LicenceCC-BY-NC-4.0. Commercial use needs a license from Jina/Elastic.MPL-2.0, free to self-host.
How you run itSelf-host the open weights or call Jina's hosted API.Local command-line tool.
HardwareGPU recommended (benchmarked on A100 and L4); falls back to CPU in Transformers.CPU only, uses all cores.
Output formatsMarkdown, HTML, LaTeX.Searchable PDF (PDF/A) and plain text.
BenchmarksOmniDocBench v1.6 overall 91.14; olmOCR-Bench overall 83.4. Scores use a stricter prompt than the recommended default.Not published
Layout and tablesPage-to-Markdown output with HTML and LaTeX options.Adds no layout, table or Markdown output.
Known failureHosted API returns HTTP 503 on cold start; retry after 30 to 60 seconds.--skip-text with default PDF/A output removes form fields (issue #1790). Can hang on PDFs whose forms share one Resources dictionary (issue #1763). --deskew --clean-final can double or quadruple file size (issue #948).

Sources

What each one is

Jina OCR

Compact page-to-Markdown model from Jina AI, built on the DeepSeek-OCR encoder.

Jina OCR 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": "jina/jina-ocr","fallbacks": ["ocrmypdf/ocrmypdf"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Jina OCR alternativesOCRmyPDF alternativesBest OCR models in 2026