Google Document AI vs Chunkr
Pick Google Document AI for bulk OCR on Google Cloud, where Enterprise OCR costs $1.50 per 1,000 pages and drops to $0.60 above 5M pages a month. Pick Chunkr for RAG chunking of PDFs, slides and Word files, or when you need to self-host layout parsing and get HTML or Markdown out. The main split is deployment: Document AI is a proprietary hosted API, while Chunkr can run on your own hardware under AGPL-3.0.
Google Document AIgoogle/document-ai | Chunkrchunkr/chunkr | |
|---|---|---|
| Type | OCR API | OCR API |
| Price | 10 credits / page | 14 credits / page |
| Per 1,000 pages | $10.00 | $14.00 |
| Typical speed | 1.4 s / page | 3.0 s / page |
| Best for | Multilingual scans | Layout-aware chunks for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 200+ languages | Multilingual |
| Max pages per request | 500 | 1,000 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | No |
| Multilingual | ✓ Yes | ✓ 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 Google Document AI if
- You run on Google Cloud and need cheap bulk OCR: $1.50 per 1,000 pages, $0.60 above 5M a month, first 1,000 free.
- You want chunking for RAG from a managed service, and Layout Parser includes it at $10 per 1,000 pages.
- You process large jobs in batch, where requests take up to 500 pages.
Choose Chunkr if
- You need to self-host with Docker, with GPU, CPU-only and Mac ARM options.
- You want HTML or Markdown output with OCR bounding boxes, from PDF, PPT, Word or image input.
- You want to point the parser at any OpenAI-compatible LLM endpoint.
Key differences
| Google Document AI | Chunkr | |
|---|---|---|
| Deployment | Hosted API only | Cloud API or self-hosted open-source version |
| Licence | Proprietary | AGPL-3.0, or a commercial license for closed use |
| Price | Enterprise OCR $1.50 per 1,000 pages; Layout Parser $10; Form Parser $30 | Hosted credit-based plans, official prices not verified; self-hosted is free but you pay for compute and an LLM endpoint |
| Output formats | JSON, plain text, bounding boxes, chunks | HTML, Markdown, JSON, bounding boxes |
| Request limits | Online requests limited to 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch 100 pages | Not published |
| Table benchmark | 64.6% on Reducto's RD-TableBench, behind Azure and Textract | Not published |
| Known weakness | Not suited to long PDFs in one synchronous call or complex tables | Open-source version uses community models, less accurate than the cloud's; no Excel support; still needs an external LLM endpoint |
Sources
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI 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.
Use one, fall back to the other
{"model": "google/document-ai","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI alternativesChunkr alternativesBest OCR models in 2026