Amazon Textract vs Chunkr
Pick Amazon Textract for English forms, invoices and large scanned PDF batches if you already run on AWS. Pick Chunkr when you need Markdown or HTML output for RAG chunking of PDFs and slides, or when you want to self-host. The main split is a metered, closed AWS API against a layout parser you can run yourself under AGPL-3.0.
Amazon Textractaws/textract | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 25 credits / page | 14 credits / page |
| Per 1,000 pages | $25.00 | $14.00 |
| Typical speed | 1.2 s / page | 3.0 s / page |
| Best for | Forms and key-value extraction | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 6 languages | Multilingual |
| Max pages per request | 3,000 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| 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
- Text detection costs $0.0015 per page ($1.50 per 1,000 pages) in US West (Oregon) for the first 1M pages a month, and the price list is published.
- 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, and it extracts tables, forms and queries, with 80.9% on RD-TableBench table accuracy.
Choose Chunkr if
- It outputs HTML, Markdown, JSON and OCR with bounding boxes, so RAG pipelines need less post-processing.
- You can self-host it with Docker on GPU, CPU-only or Mac ARM, and the open-source version is free apart from compute and an LLM endpoint.
- It accepts PDF, PPT, Word and images, and works with any OpenAI-compatible LLM endpoint.
Key differences
| Amazon Textract | Chunkr | |
|---|---|---|
| How you run it | Hosted AWS API only. | Cloud API or self-host with Docker (GPU, CPU-only, Mac ARM). |
| Licence | Proprietary. | AGPL-3.0, or a commercial licence. Closed-source products need the commercial licence. |
| Price | Text $0.0015/page, Tables $0.015, Forms $0.05, Queries $0.015 (US West Oregon, first 1M pages a month). | Hosted credit-based plans, official prices not verified. Open-source version is free but you pay for compute and an LLM endpoint. |
| Output formats | JSON, plain text, bounding boxes. Markdown needs post-processing. | HTML, Markdown, JSON, bounding boxes. |
| Input and size limits | Async API handles PDFs up to 500 MB and 3,000 pages. The sync API takes one page. | PDF, PPT, Word and images. Excel is not supported in the open-source version. |
| 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. | No language or handwriting details published. |
| Benchmark and accuracy | 80.9% on RD-TableBench table accuracy (independent). | No benchmark listed. The open-source version uses community models that are less accurate than the cloud's in-house models. |
Sources
What each one is
Amazon Textract
AWS OCR with form key-value pairs, tables and per-word confidence scores.
Amazon Textract detailsChunkr
Document parsing API that segments and chunks pages for RAG. Self-hostable version available.
Chunkr detailsTry 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": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Amazon Textract vs ABBYY FineReaderAmazon Textract vs UnstructuredAzure Document Intelligence vs ChunkrMarker vs ChunkrAmazon Textract vs TesseractPhi-4-multimodal vs ChunkrAmazon Textract vs Azure Document IntelligenceGemini Flash vs Chunkr
Amazon Textract alternativesChunkr alternativesBest OCR models in 2026