OCRRouter

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answering over charts and documents or an existing Mistral API integration, because Mistral marks it deprecated and no longer maintained.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/textractPixtralmistral/pixtral
TypeOCR APIVision model
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page3.0 s / page
Best forForms and key-value extractionQuestions about document images
InputsPDF, imagesimages
Languages6 languagesMultilingual
Max pages per request3,000500
Tables✓ YesNo
Handwriting✓ YesNo
MathNoNo
Bounding boxes✓ YesNo
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

  • 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 TextractPixtral
DeploymentHosted AWS API onlyMistral API or self-hosted open weights
LicenceProprietaryApache-2.0
PriceFirst 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 formatsJSON, plain text, bounding boxes. No Markdown without post-processingPlain text, Markdown, JSON
Languages and handwritingText detection covers English, French, German, Italian, Portuguese and Spanish. Handwriting and Queries are English only. Vertical Japanese and Chinese are not supportedReported accuracy drop on handwriting, small fonts and non-Latin scripts (third-party guide)
BenchmarkRD-TableBench table accuracy 80.9% (independent)DocVQA 90.7 ANLS, ChartQA 81.8, MMMU 52.5 (all from Mistral)
Known failureSync API takes one pageDeprecated 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

What each one is

Amazon Textract

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

Amazon Textract details

Pixtral

Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.

Pixtral 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": ["mistral/pixtral"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesPixtral alternativesBest OCR models in 2026