Amazon Textract vs dots.ocr
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where a managed API with per-page pricing and confidence scores fits. Pick dots.ocr for multilingual documents that need Markdown with layout, and when you can run a GPU yourself. The main split is a hosted, proprietary, English-leaning API versus a free, MIT-licensed model you host.
Amazon Textractaws/textract | dots.ocrrednote/dots-ocr | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 1.2 s / page | 1.5 s / page |
| Best for | Forms and key-value extraction | Multilingual document parsing |
| Inputs | PDF, images | PDF, images |
| Languages | 6 languages | 100+ languages |
| Max pages per request | 3,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
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 forms, tables and queries through one AWS API, with Detect Document Text at $0.0015 per page for the first 1M pages a month.
- The async API takes PDFs up to 500 MB and 3,000 pages, which suits large scanned batches.
- It returns word and line geometry with confidence scores, and you run no GPU.
Choose dots.ocr if
- The code is MIT licensed and free to self-host, so you pay only for compute.
- One pass returns layout boxes, categories and text, with tables as HTML and formulas as LaTeX, and Markdown output for RAG.
- It is a multilingual parser, so it avoids Textract's limit of six Latin-script languages and its lack of vertical Japanese and Chinese.
Key differences
| Amazon Textract | dots.ocr | |
|---|---|---|
| How you run it | Hosted AWS API | Self-hosted via vLLM or Hugging Face Transformers; a single CUDA GPU with vLLM is the documented path |
| Licence | Proprietary | MIT, plus a separate dots.ocr license agreement file in the repository |
| Price | US West (Oregon), first 1M pages/month: text $0.0015/page, Tables $0.015, Forms $0.05, Queries $0.015 | Free, you pay for compute |
| Output formats | JSON, plain text, bounding boxes | JSON, Markdown, HTML, LaTeX, bounding boxes, SVG |
| Languages | Text detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only. | Described as multilingual; a language list is not published |
| Benchmark | 80.9% on RD-TableBench table accuracy (independent) | 79.1 on olmOCR-bench for dots.ocr and 83.9 for dots.mocr 1.5, both reported by the authors |
| Known failure | Sync API takes one page; vertical Japanese and Chinese text not supported | Runs of ellipses or underscores can make output repeat endlessly; a table above 1000 grid cells raised an error and dropped the page in Docling |
Sources
- Textract pricing
- Textract quotas
- Textract hard limits
- Reducto RD-TableBench
- dots.ocr GitHub README
- Docling issue #5146
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsdots.ocr
Single vision model from rednote that does layout detection and content recognition together.
dots.ocr detailsTry both on your own file
Run the file once with each model and compare the output.
Use one, fall back to the other
{"model": "aws/textract","fallbacks": ["rednote/dots-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesdots.ocr alternativesBest OCR models in 2026