OCRRouter

Google Cloud Vision OCR vs Chunkr

Pick Google Cloud Vision OCR for plain text extraction from photos, signs, labels and handwritten notes, especially at high volume, where its per-page price is low and it returns word-level bounding boxes. Pick Chunkr when you need structured Markdown, HTML or JSON from PDFs, slides and Word files for RAG, or when you must self-host. The main split is output: Cloud Vision returns text with positions and no layout, while Chunkr parses layout and chunks the document.

Google Cloud Vision OCRgoogle/cloud-visionChunkrchunkr/chunkr
TypeOCR APIOCR API
Price2 credits / page14 credits / page
Per 1,000 pages$2.00$14.00
Typical speed1.0 s / page3.0 s / page
Best forPhotos and simple scansLayout-aware chunks for RAG
InputsPDF, imagesPDF, images, DOCX
Languages100+ languagesMultilingual
Max pages per request2,0001,000
TablesNo✓ Yes
Handwriting✓ YesNo
MathNo✓ Yes
Bounding boxes✓ Yes✓ Yes
Confidence✓ YesNo
FormsNoNo
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 Cloud Vision OCR if

  • It is built for photos of signs and labels (TEXT_DETECTION) and dense documents (DOCUMENT_TEXT_DETECTION), with handwriting supported through language hints.
  • It returns a page, block, paragraph, word and symbol hierarchy with bounding polygons, so you can work at whatever level you need.
  • Pricing is published and falls from $1.50 to $0.60 per 1,000 units above 5M, with the first 1,000 units per month free for each feature.

Choose Chunkr if

  • It outputs HTML, Markdown, JSON and OCR with bounding boxes, and does layout analysis and semantic chunking, which suits RAG over PDFs and slides.
  • It accepts PDF, PPT, Word and images, so one service covers common office formats.
  • You can self-host it with Docker (GPU, CPU-only or Mac ARM) under AGPL-3.0, or buy a commercial license for closed-source use.

Key differences

Google Cloud Vision OCRChunkr
How you run itHosted API on Google Cloud, over REST or client libraries. No on-premise option.Cloud API or self-hosted via Docker. Self-host still needs an external OpenAI-compatible LLM endpoint.
LicenceProprietaryAGPL-3.0 or commercial license
PriceFirst 1,000 units per month free per feature, then $1.50 per 1,000 units up to 5M, $0.60 per 1,000 above. Each PDF page is one unit.Hosted credit-based plans, official prices not published. Open-source version is free, but you pay for compute and an LLM endpoint.
Output formatsJSON, plain text, bounding boxes. No Markdown, so you rebuild reading order yourself.HTML, Markdown, JSON, bounding boxes
Tables and layoutNo table or layout structure. Google points to Document AI for forms and tables.Does layout analysis and semantic chunking
HandwritingSupported via DOCUMENT_TEXT_DETECTION and language hintsNot published
Input and limitsPDF and TIFF need async processing via Cloud Storage. Async batch takes up to 2,000 image files per request. Billing must be enabled even for the free units.PDF, PPT, Word and images. Excel is not supported in the open-source version.

Sources

What each one is

Google Cloud Vision OCR

Google Cloud's image OCR with text and document text detection, word boxes and confidence.

Google Cloud Vision OCR 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/cloud-vision","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Google Cloud Vision OCR alternativesChunkr alternativesBest OCR models in 2026