Amazon Textract vs Typhoon OCR
Pick Amazon Textract for English forms and invoices on AWS, and for large scanned PDF batches, where basic text detection costs $1.50 per 1,000 pages. Pick Typhoon OCR for Thai and Thai-English documents such as government forms and financial reports, or when you need Markdown, HTML or LaTeX output from a model you can self-host. Textract does not cover Thai and Typhoon OCR is only evaluated on Thai and English, so language usually decides it.
Amazon Textractaws/textract | Typhoon OCRtyphoon/typhoon-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 | 1.8 s / page |
| Best for | Forms and key-value extraction | Thai documents |
| Inputs | PDF, images | PDF, images |
| Languages | 6 languages | Thai, English |
| Max pages per request | 3,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| 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
- You run on AWS and want a managed API with no model to host.
- You process large scanned PDFs: the async API handles files up to 500 MB and 3,000 pages.
- You need word and line geometry with confidence scores, or forms, tables and queries on English documents.
Choose Typhoon OCR if
- Your documents are Thai or mixed Thai and English: V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870).
- You want to self-host under Apache-2.0 (subject to OpenTyphoon Terms and Conditions) and pay only for compute.
- You need Markdown, HTML or LaTeX output, with tables as HTML with merged cells, equations as LaTeX and checkboxes marked.
Key differences
| Amazon Textract | Typhoon OCR | |
|---|---|---|
| How you run it | Hosted API only | Self-host the weights, or use the Typhoon API (typhoon-ocr-v2) |
| Licence | Proprietary | Apache-2.0, subject to OpenTyphoon Terms and Conditions |
| Price | US West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015/page, Forms $0.05/page, Queries $0.015/page | Free self-hosted (you pay for compute); API pricing not listed |
| Output formats | JSON, plain text, bounding boxes | Markdown, HTML, LaTeX |
| Languages | Text detection: English, French, German, Italian, Portuguese, Spanish. Handwriting and Queries: English only | Thai and English only evaluated |
| Benchmarks | 80.9% on RD-TableBench (independent) | olmOCR-bench 84.7, OmniDocBench v1.6 90.97, ThaiOCRBench 59.9 (V2 2B, from the authors) |
| Known failure | Vertical Japanese and Chinese text not supported; sync API takes one page | V2 can loop until the token limit on dense multi-column pages; key-information extraction scores 21.0 on ThaiOCRBench |
Sources
- Textract pricing
- Textract quotas
- Reducto RD-TableBench
- Typhoon OCR V2 2B model card
- Typhoon OCR technical report
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsTyphoon OCR
Open vision model tuned for Thai and English documents, with Markdown output.
Typhoon 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": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesTyphoon OCR alternativesBest OCR models in 2026