OCRRouter

Azure Document Intelligence vs Kraken

Pick Kraken for historical manuscripts, early prints and right-to-left or non-Latin scripts, where you can train recognition on your own material and run it free on Linux or macOS. Pick Azure Document Intelligence for modern business documents such as invoices, receipts and IDs, where prebuilt models work without training. The main split is the document type: Kraken is built for historical material and Azure is built for business forms.

Azure Document Intelligenceazure/document-intelligenceKrakenkraken/kraken
TypeOCR APIOpen source
Price60 credits / page1 credit / page
Per 1,000 pages$60.00$1.00
Typical speed1.5 s / page1.5 s / page
Best forEnterprise forms and IDsHistorical documents and manuscripts
InputsPDF, imagesimages
Languages300+ languagesMany scripts, incl. right-to-left
Max pages per request2,000500
Tables✓ YesNo
Handwriting✓ Yes✓ Yes
MathNoNo
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
Forms✓ YesNo
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 Azure Document Intelligence if

  • Prebuilt models cover invoices, receipts, IDs, W-2 and contracts, so you need no training to extract those fields.
  • It is a managed service billed per page: Read is $1.50 per 1,000 pages ($0.60 above 1M), and the first 500 pages a month are free.
  • Disconnected containers let you run it on-prem, and it fits teams already on Azure.

Choose Kraken if

  • It is built for historical manuscripts and early prints, with right-to-left, BiDi and top-to-bottom script support.
  • Layout analysis, reading order and character recognition are all trainable, and a public Zenodo repository holds community-trained models.
  • It is Apache-2.0 and free to self-host, and it writes ALTO, PageXML, abbyyXML and hOCR for digital humanities tools.

Key differences

Azure Document IntelligenceKraken
Best-fit documentsInvoices, receipts and ID documentsHistorical manuscripts, early prints, Arabic, Hebrew and other RTL scripts
LicenceProprietaryApache-2.0
How you run itManaged service, plus containers including disconnected on-prem usePython library installed with pip on Linux or macOS (x64 or ARM, Python 3.10 to 3.13); no Windows support
PriceRead $1.50 per 1,000 pages; Layout and prebuilt $10 per 1,000; custom extraction $30 per 1,000; 500 free pages a monthFree; you pay for your own compute
Output formatsJSON, Markdown, plain text, bounding boxes, searchable PDFALTO, PageXML, hOCR, plain text, bounding boxes
Table benchmark82.7% on RD-TableBench (independent)Not published
Known problemsStacked models multiply cost (Prebuilt plus Layout plus high-res add-on is $26 per 1,000 pages); the free tier reads only the first two pages of each documentInstall can fail with a dependency conflict (issue #816); learned line order is lost in segmentation and text output (issue #820); usually needs training on your own material

Sources

What each one is

Azure Document Intelligence

Azure layout model with tables, selection marks and prebuilt invoice and ID readers.

Azure Document Intelligence details

Kraken

OCR engine for historical documents and manuscripts, with trainable models for unusual scripts.

Kraken 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": "azure/document-intelligence","fallbacks": ["kraken/kraken"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Azure Document Intelligence alternativesKraken alternativesBest OCR models in 2026