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/textract | MiniCPM-V 4.5openbmb/minicpm-v | |
|---|---|---|
| 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 | 2.5 s / page |
| Best for | Forms and key-value extraction | OCR on edge devices |
| Inputs | PDF, images | images |
| Languages | 6 languages | 30+ languages |
| Max pages per request | 3,000 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | ✓ Yes |
| 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 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 Textract | MiniCPM-V 4.5 | |
|---|---|---|
| How you run it | Hosted AWS API | Self-host with llama.cpp, vLLM or Transformers |
| Licence | Proprietary | Apache-2.0 |
| Price | US West (Oregon), first 1M pages/month: text detection $0.0015/page, Tables $0.015, Forms $0.05, Queries $0.015 | Free; you pay for compute |
| Output formats | JSON, plain text, bounding boxes | Plain text, Markdown, JSON |
| Coordinates and layout | Word and line geometry with confidence scores | No bounding box or layout output |
| Languages | Text detection covers English, French, German, Italian, Portuguese and Spanish; handwriting and Queries are English only | Not published |
| Benchmarks | 80.9% 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 detailsMiniCPM-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 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": ["openbmb/minicpm-v"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract alternativesMiniCPM-V 4.5 alternativesBest OCR models in 2026