OCRRouter

Google Document AI vs MinerU

Pick Google Document AI if you already run on Google Cloud and want a hosted API for bulk OCR or RAG chunking, billed per page. Pick MinerU if you want to self-host, convert mixed PDF and Office files to Markdown, LaTeX or DOCX, or run on CPU. The main split is a managed, per-page-priced API against a free toolkit where you pay for compute.

Google Document AIgoogle/document-aiMinerUopendatalab/mineru
TypeOCR APIOpen source
Price10 credits / page2 credits / page
Per 1,000 pages$10.00$2.00
Typical speed1.4 s / page2.0 s / page
Best forMultilingual scansAcademic PDFs
InputsPDF, imagesPDF, images
Languages200+ languages80+ languages
Max pages per request500500
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

  • Enterprise Document OCR costs $1.50 per 1,000 pages, drops to $0.60 above 5M pages a month, and the first 1,000 pages are free.
  • Layout Parser includes chunking for RAG at $10 per 1,000 pages, so you do not build your own chunker.
  • Batch requests take up to 500 pages, which suits bulk OCR jobs on Google Cloud.

Choose MinerU if

  • It is free to self-host, so you pay only for compute, and the basic tier runs on CPU with about 2 GB RAM.
  • It accepts PDF, images, DOCX, PPTX, XLSX, EPUB, OFD and HTML, and renders to Markdown, HTML, LaTeX, DOCX, EPUB and JSON.
  • It suits Chinese and English academic papers, and the VLM tier reaches 2.12 pages per second on one A100 with vLLM.

Key differences

Google Document AIMinerU
How you run itHosted API on Google CloudSelf-host as CLI, API or WebUI
LicenceProprietaryMinerU Open Source License (Apache-2.0 based with extra conditions); MinerU2.5 VLM weights tagged AGPL-3.0
PriceOCR $1.50 per 1,000 pages ($0.60 above 5M a month, first 1,000 free); Layout Parser $10; Form Parser $30 per 1,000 pagesFree, you pay for compute
Request limitsOnline requests 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch 100 pagesNot published
HardwareNone to manageBasic tier: CPU, 2 GB RAM. VLM tiers: 16 GB RAM and a GPU with 8 GB+ VRAM
Output formatsJSON, plain text, bounding boxes, chunksMarkdown, HTML, LaTeX, DOCX, EPUB, JSON
Tables and known failures64.6% on RD-TableBench, behind Azure and TextractVLM tiers drop merged header rows, such as bank statement account lines (issue #5554); VLM pipeline can repeat content and produce 300 KB figure blocks (issue #5728)

Sources

What each one is

Google Document AI

Google Cloud OCR with layout parsing and specialised processors.

Google Document AI details

MinerU

Open-source PDF to Markdown pipeline popular for academic and Chinese documents.

MinerU 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": ["opendatalab/mineru"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Google Document AI alternativesMinerU alternativesBest OCR models in 2026