OCRRouter

Amazon Textract vs SmolDocling

Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want a managed API and pay per page. Pick SmolDocling only for experiments or low-budget English page conversion that you self-host, because it is a preview release and the authors point users to Granite-Docling.

Amazon Textractaws/textractSmolDoclinghuggingface/smoldocling
TypeOCR APIOpen source
Price25 credits / page1 credit / page
Per 1,000 pages$25.00$1.00
Typical speed1.2 s / page1.0 s / page
Best forForms and key-value extractionVery cheap page conversion
InputsPDF, imagesPDF, images
Languages6 languagesMainly English
Max pages per request3,000500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
Forms✓ YesNo
MultilingualNoNo
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 is a hosted API with an async mode that takes PDFs up to 500 MB and 3,000 pages, so you run no infrastructure.
  • It extracts forms, tables and queries, and returns word and line geometry with confidence scores.
  • Basic text detection costs $1.50 per 1,000 pages, and it supports six Latin-script languages instead of English only.

Choose SmolDocling if

  • It is free to license and run, and you pay only for your own compute.
  • At 256M parameters it runs on modest hardware, and it takes about 0.35 seconds per page on an A100 with vLLM.
  • It outputs Markdown, HTML, JSON, LaTeX and DocTags from one model, so you do not need to post-process into Markdown for RAG.

Key differences

Amazon TextractSmolDocling
How you run itHosted AWS APISelf-hosted 256M-parameter model
LicenceProprietaryApache-2.0 per the model summary (metadata tag says CDLA-Permissive-2.0)
PriceDetect Document Text $0.0015/page, Tables $0.015/page, Forms $0.05/page, Queries $0.015/page (US West, first 1M pages/month)Free, you pay for compute
Output formatsJSON, plain text, bounding boxesDocTags, Markdown, HTML, JSON, LaTeX, bounding boxes
LanguagesText detection in English, French, German, Italian, Portuguese and Spanish. Handwriting and Queries are English only.English only
Table benchmark80.9% on RD-TableBench (independent)TEDS structure 0.82 on FinTabNet at 150dpi (reported by the authors, a different test)
Known failureNo vertical Japanese or Chinese text. The sync API takes one page.Output can loop on some images and become very slow. Endless token repetition and missing closing tags are listed as typical defects.

Sources

What each one is

Amazon Textract

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

Amazon Textract details

SmolDocling

Tiny 256M vision model from Hugging Face and IBM that outputs DocTags. Predecessor of Granite Docling.

SmolDocling 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": ["huggingface/smoldocling"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesSmolDocling alternativesBest OCR models in 2026