OCRRouter

Amazon Textract vs Unlimited OCR

Pick Amazon Textract for English forms, invoices and large scanned PDF batches if you already run on AWS and want a managed API with per-page pricing. Pick Unlimited OCR for long reports and books that you want as Markdown or text with boxes in one request, if you can run an NVIDIA GPU or use the Baidu Cloud endpoint. The main split is hosted AWS API with language limits versus an MIT-licensed self-hosted model with GPU needs and reported looping and hallucination.

Amazon Textractaws/textractUnlimited OCRbaidu/unlimited-ocr
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page1.2 s / page
Best forForms and key-value extractionBooks and very long documents
InputsPDF, imagesPDF, images
Languages6 languages30+ languages
Max pages per request3,0001,000
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
Forms✓ YesNo
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

  • Basic text detection costs $0.0015 per page ($1.50 per 1,000 pages) in US West (Oregon) for the first 1M pages a month, with no GPU to run.
  • The async API handles PDFs up to 500 MB and 3,000 pages, and returns word and line geometry with confidence scores.
  • It extracts tables, forms and queries through the AWS API, and scores 80.9% on RD-TableBench table accuracy in an independent test.

Choose Unlimited OCR if

  • It is MIT licensed, so you can use it commercially with no copyleft, and self-hosting costs only your compute.
  • It parses 40+ pages in a single forward pass with roughly constant memory, and outputs Markdown, plain text and bounding boxes.
  • You are not tied to a cloud: run it with vLLM, SGLang or transformers, or use the hosted endpoint in Baidu Cloud's OCR product.

Key differences

Amazon TextractUnlimited OCR
How you run itHosted AWS API onlySelf-host with vLLM, SGLang or transformers, or hosted in Baidu Cloud
LicenceProprietaryMIT
Price$0.0015/page text detection, $0.015 Tables, $0.05 Forms, $0.015 Queries (US West Oregon, first 1M pages/month)Free self-hosted, you pay for compute; hosted price Not published
Output formatsJSON, plain text, bounding boxes (no Markdown without post-processing)Markdown, plain text, bounding boxes
Document sizeAsync API: PDFs up to 500 MB and 3,000 pages; sync API takes one page40+ pages in one pass; context capped at 32,768 tokens, multi-page input only in base mode
LanguagesText detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. No vertical Japanese or ChineseNot published
Known failures and hardwareNot publishedRepetition loops (issue #55), hallucinated text (issue #58), little bold or italic styling kept, needs an NVIDIA GPU; version 2 runs out of memory on 12 GB GPUs under SGLang

Sources

What each one is

Amazon Textract

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

Amazon Textract details

Unlimited OCR

Open-source model from Baidu that reads hundreds of pages in one pass with flat memory use.

Unlimited 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": ["baidu/unlimited-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesUnlimited OCR alternativesBest OCR models in 2026