OCRRouter

Amazon Textract vs olmOCR

Pick Amazon Textract for English forms, invoices and large scanned PDF batches if you already run on AWS and want a managed API. Pick olmOCR for large-scale PDF to Markdown, academic papers with equations, or mixed printed and handwritten pages, if you can run a GPU with at least 12 GB VRAM or use a hosted endpoint. The main split is a proprietary per-page API against an open 7B model that outputs Markdown.

Amazon Textractaws/textractolmOCRallenai/olmocr
TypeOCR APIOpen source
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page1.5 s / page
Best forForms and key-value extractionBulk PDF to text for datasets
InputsPDF, imagesPDF, images
Languages6 languagesMainly English
Max pages per request3,0001,000
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
MathNo✓ Yes
Bounding boxes✓ YesNo
Confidence✓ YesNo
Forms✓ YesNo
MultilingualNoNo
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 $1.50 per 1,000 pages, and you pay nothing for servers or GPUs.
  • 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, plus dedicated Forms, Tables and Queries features for English forms and invoices.

Choose olmOCR if

  • It outputs clean Markdown in natural reading order, with headers and footers removed, which fits RAG and LLM training data.
  • It handles equations, tables and handwriting, so it suits academic papers and mixed printed and handwritten pages.
  • The toolkit is Apache-2.0 and the weights, training data and code are open, with self-hosting under $200 per million pages per Ai2.

Key differences

Amazon TextractolmOCR
LicenceProprietaryApache-2.0 (toolkit); weights, training data and code released
How you run itHosted AWS API onlySelf-host with vLLM on an NVIDIA GPU with at least 12 GB VRAM and 30 GB free disk, or use third-party hosted endpoints
PriceUS West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015/page, Forms $0.05/page, Queries $0.015/pageSelf-hosted under $200 per million pages per Ai2; DeepInfra hosted olmOCR-2-7B $0.09 input / $0.19 output per million tokens
Output formatsJSON, plain text, bounding boxesMarkdown, JSON
Benchmark80.9% on RD-TableBench table accuracy (independent)82.4 on olmOCR-Bench v0.4.0 (reported by the authors); a different test, so the scores are not comparable
Languages and handwritingText detection covers English, French, German, Italian, Portuguese and Spanish; handwriting and Queries are English only; vertical Japanese and Chinese not supportedNot published
Known failure modesSync API takes one page; no Markdown output without post-processingOut of memory on a 12 GB GPU (issue #424), gets stuck on the last few pages (issue #433), unreliable image bounding boxes (issue #437), hard to install into an existing Python environment

Sources

What each one is

Amazon Textract

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

Amazon Textract details

olmOCR

Open-source vision model from Ai2 (often searched as olm ocr) that turns PDFs into clean, reading-order text. Latest release: olmOCR 2.

olmOCR 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": ["allenai/olmocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesolmOCR alternativesBest OCR models in 2026