OCRRouter

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-aiChunkrchunkr/chunkr
TypeOCR APIOCR API
Price10 credits / page14 credits / page
Per 1,000 pages$10.00$14.00
Typical speed1.4 s / page3.0 s / page
Best forMultilingual scansLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
Languages200+ languagesMultilingual
Max pages per request5001,000
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
Forms✓ YesNo
Multilingual✓ Yes✓ 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 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 AIChunkr
DeploymentHosted API onlyCloud API or self-hosted open-source version
LicenceProprietaryAGPL-3.0, or a commercial license for closed use
PriceEnterprise OCR $1.50 per 1,000 pages; Layout Parser $10; Form Parser $30Hosted credit-based plans, official prices not verified; self-hosted is free but you pay for compute and an LLM endpoint
Output formatsJSON, plain text, bounding boxes, chunksHTML, Markdown, JSON, bounding boxes
Request limitsOnline requests limited to 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch 100 pagesNot published
Table benchmark64.6% on Reducto's RD-TableBench, behind Azure and TextractNot published
Known weaknessNot suited to long PDFs in one synchronous call or complex tablesOpen-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 details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr 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": "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