OCRRouter

Amazon Textract vs MiniCPM-V 4.5

Pick Amazon Textract for English forms, invoices and large scanned PDF batches on AWS, where you want a managed API with word and line coordinates. Pick MiniCPM-V 4.5 if you want to self-host under Apache-2.0 and run quantized OCR or document Q&A on your own GPU or edge device. The main split is a hosted, per-page-priced service with geometry output against a free open-weight model with no coordinates.

Amazon Textractaws/textractMiniCPM-V 4.5openbmb/minicpm-v
TypeOCR APIVision model
Price25 credits / page2 credits / page
Per 1,000 pages$25.00$2.00
Typical speed1.2 s / page2.5 s / page
Best forForms and key-value extractionOCR on edge devices
InputsPDF, imagesimages
Languages6 languages30+ languages
Max pages per request3,000500
Tables✓ Yes✓ Yes
Handwriting✓ Yes✓ Yes
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 returns word and line geometry with confidence scores, so you get bounding boxes for every result.
  • The async API takes 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 Tables, Forms and Queries are separate per-page features.

Choose MiniCPM-V 4.5 if

  • The weights and code are Apache-2.0, and you pay only for your own compute.
  • It runs on llama.cpp and vLLM with int4, GGUF and AWQ builds, so you can run it on a single GPU or at the edge.
  • It outputs plain text, Markdown or JSON, which suits local document Q&A.

Key differences

Amazon TextractMiniCPM-V 4.5
How you run itHosted AWS APISelf-host with llama.cpp, vLLM or Transformers
LicenceProprietaryApache-2.0
PriceUS West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015, Forms $0.05, Queries $0.015Free; you pay for compute
Output formatsJSON, plain text, bounding boxesPlain text, Markdown, JSON
Coordinates and layoutWord and line geometry with confidence scoresNo bounding box or layout output
LanguagesText detection covers English, French, German, Italian, Portuguese and Spanish; handwriting and Queries are English onlyNot published
Benchmarks80.9% on RD-TableBench table accuracy (independent)Vendor claims only, with scores given as images on the model card, so numbers are hard to verify

Sources

What each one is

Amazon Textract

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

Amazon Textract details

MiniCPM-V 4.5

8B vision model from OpenBMB (August 2025) built to run on devices, with strong OCR and document parsing.

MiniCPM-V 4.5 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": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Amazon Textract alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026