Google Document AI vs Docling
Pick Docling if you want to run the parser yourself, for free, on born-digital PDFs and Office files that feed a RAG pipeline. Pick Google Document AI if you want a hosted API with per-page pricing for bulk OCR on Google Cloud. The main split is how you run it: Docling is an MIT-licensed library you host and pay for in compute, while Document AI is a proprietary API billed per 1,000 pages.
Google Document AIgoogle/document-ai | Doclingibm/docling | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 10 credits / page | 2 credits / page |
| Per 1,000 pages | $10.00 | $2.00 |
| Typical speed | 1.4 s / page | 2.2 s / page |
| Best for | Multilingual scans | Structured export for RAG |
| Inputs | PDF, images | PDF, images, DOCX |
| Languages | 200+ languages | Latin scripts, CJK |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | ✓ Yes |
| Handwriting | ✓ Yes | No |
| Math | No | ✓ Yes |
| Bounding boxes | ✓ Yes | ✓ Yes |
| Confidence | ✓ Yes | No |
| Forms | ✓ Yes | No |
| Multilingual | ✓ Yes | No |
| 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
- 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 large backlogs of scanned files on Google Cloud.
Choose Docling if
- It is MIT licensed and free to self-host, so you pay only for compute and keep documents on your own machines.
- One API reads PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails and XBRL, and exports lossless JSON with layout, reading order and table structure.
- You can plug in EasyOCR, Tesseract or RapidOCR, or a 258M-parameter GraniteDocling VLM, and it runs on CPU on macOS, Linux and Windows.
Key differences
| Google Document AI | Docling | |
|---|---|---|
| How you run it | Hosted API on Google Cloud | Python library, runs locally on CPU or GPU |
| Licence | Proprietary | MIT (individual models have their own licences) |
| Price | OCR $1.50 per 1,000 pages ($0.60 above 5M a month); Layout Parser $10; Form Parser $30 | Free, self-hosted; you pay for compute |
| Input formats | Not published | PDF, DOCX, PPTX, XLSX, HTML, EPUB, images, emails, XBRL |
| Output formats | JSON, plain text, bounding boxes, chunks | Markdown, HTML, JSON, DocTags, plain text |
| Request limits | Online: 15 pages (30 in imageless mode). Batch: 500 pages. Form Parser batch: 100 pages. | Not published |
| Known failure | 64.6% on RD-TableBench, behind Azure and Textract; weak on complex tables | OCR regression in 2.143.1 drops words and numbers with full-page Tesseract OCR (issue #5254); reading order can merge neighbouring columns (issue #5132) |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- Supported formats
- Issue #5254 OCR regression
- Issue #5132 reading order
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI 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": "google/document-ai","fallbacks": ["ibm/docling"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI vs TesseractGoogle Document AI vs MinerUDeepSeek-OCR vs DoclingAzure Document Intelligence vs DoclingLlamaParse vs DoclingPaddleOCR-VL vs DoclingMinerU vs DoclingDocling vs Tesseract
Google Document AI alternativesDocling alternativesBest OCR models in 2026