OCRRouter

Amazon Textract vs Nanonets-OCR

Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want JSON with bounding boxes and confidence scores from a managed API. Pick Nanonets-OCR if you want to self-host and turn printed business documents into Markdown for LLMs, including signatures, checkboxes and flowcharts. Avoid Nanonets-OCR for handwriting, and avoid Textract for Chinese, Japanese or other non-Latin text.

Amazon Textractaws/textractNanonets-OCRnanonets/nanonets-ocr
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page1.8 s / page
Best forForms and key-value extractionMarkdown with semantic tags
InputsPDF, imagesPDF, images
Languages6 languagesMultilingual
Max pages per request3,000500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
Forms✓ Yes✓ Yes
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 Amazon Textract if

  • It handles large scanned PDF batches: the async API takes PDFs up to 500 MB and 3,000 pages.
  • It returns word and line geometry with confidence scores, so you can check and place text in JSON or bounding boxes.
  • Basic text detection costs $0.0015 per page, with Tables at $0.015, Forms at $0.05 and Queries at $0.015 for the first 1M pages a month in US West (Oregon).

Choose Nanonets-OCR if

  • It outputs Markdown, HTML, LaTeX and Mermaid, so printed PDFs go to LLMs with no post-processing and flowcharts and org charts become Mermaid code.
  • It tags signatures, watermarks and image descriptions, and converts checkboxes to unicode symbols, which suits business documents.
  • The weights are on Hugging Face and free to self-host, so you pay only for compute and keep documents on your own hardware.

Key differences

Amazon TextractNanonets-OCR
How you run itHosted API on AWSSelf-host the weights from Hugging Face
LicenceProprietaryNot stated on the Nanonets-OCR2-3B model card (no license tag); base model is Qwen2.5-VL-3B
PriceFrom $0.0015 per page for text detection; Forms $0.05 per pageFree to self-host; you pay for compute
Output formatsJSON, plain text, bounding boxesMarkdown, HTML, LaTeX, Mermaid
BenchmarkRD-TableBench table accuracy 80.9% (independent)olmOCR-bench overall 69.5 and DocVQA 89.43 for OCR2-3B (reported by the authors)
HandwritingSupported, English onlyNot trained on handwriting; can hallucinate, and one test saw generation loops with CER up to 2100%
Languages and limitsText detection covers English, French, German, Italian, Portuguese and Spanish; no vertical Japanese or Chinese; sync API takes one pageFixed prompt; custom extraction prompts are expected to hallucinate

Sources

What each one is

Amazon Textract

AWS OCR with form key-value pairs, tables and per-word confidence scores.

Amazon Textract details

Nanonets-OCR

Open image-to-Markdown model that tags tables, equations, signatures, watermarks and checkboxes.

Nanonets-OCR 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": "aws/textract","fallbacks": ["nanonets/nanonets-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesNanonets-OCR alternativesBest OCR models in 2026