Amazon Textract vs Pixtral
Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you get structured tables, forms and geometry with confidence scores. Pixtral 12B only fits question answering over charts and documents or an existing Mistral API integration, because Mistral marks it deprecated and no longer maintained. Do not start a new production OCR project on Pixtral.
Amazon Textractaws/textract | Pixtralmistral/pixtral | |
|---|---|---|
| Type | OCR API | Vision model |
| Price | 25 credits / page | 2 credits / page |
| Per 1,000 pages | $25.00 | $2.00 |
| Typical speed | 1.2 s / page | 3.0 s / page |
| Best for | Forms and key-value extraction | Questions about document images |
| Inputs | PDF, images | images |
| Languages | 6 languages | Multilingual |
| Max pages per request | 3,000 | 500 |
| Tables | ✓ Yes | No |
| 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
- It extracts tables, forms and queries and returns word and line geometry with confidence scores, as JSON, plain text or bounding boxes.
- The async API handles PDFs up to 500 MB and 3,000 pages, which suits large scanned batches.
- Basic text detection costs $1.50 per 1,000 pages, and it scored 80.9% on RD-TableBench table accuracy (independent test).
Choose Pixtral if
- It is open weights under Apache-2.0, so you can self-host it and pay only for compute.
- It scored 90.7 ANLS on DocVQA (reported by Mistral) and can answer questions about charts and documents.
- The 128K token context allows many images per request, and the launch API price was $0.15 per million tokens.
Key differences
| Amazon Textract | Pixtral | |
|---|---|---|
| Deployment | Hosted AWS API only | Mistral API or self-hosted open weights |
| Licence | Proprietary | Apache-2.0 |
| Price | First 1M pages/month in US West (Oregon): $0.0015/page for text, $0.015 for Tables, $0.05 for Forms, $0.015 for Queries | $0.15 per million input and output tokens at launch; free to self-host, you pay for compute |
| Output formats | JSON, plain text, bounding boxes. No Markdown without post-processing | Plain text, Markdown, JSON |
| Languages and handwriting | Text detection covers English, French, German, Italian, Portuguese and Spanish. Handwriting and Queries are English only. Vertical Japanese and Chinese are not supported | Reported accuracy drop on handwriting, small fonts and non-Latin scripts (third-party guide) |
| Benchmark | RD-TableBench table accuracy 80.9% (independent) | DocVQA 90.7 ANLS, ChartQA 81.8, MMMU 52.5 (all from Mistral) |
| Known failure | Sync API takes one page | Deprecated and no longer maintained; a HN launch thread user said it does not always get OCR near correct; Q4 quantization reported to degrade small text OCR |
Sources
- Textract pricing
- Textract quotas
- Textract hard limits
- Reducto RD-TableBench
- Mistral announcement
- HN launch thread
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsPixtral
Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.
Pixtral 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": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesPixtral alternativesBest OCR models in 2026