Google Document AI vs Florence-2
Pick Google Document AI for bulk OCR of scanned business documents on Google Cloud, or when you need RAG chunks from Layout Parser. Pick Florence-2 for short English text in images with bounding boxes, run on your own hardware under an MIT licence. Neither one is built for complex tables: Document AI scored 64.6% on RD-TableBench, and Florence-2 returns only text and boxes.
Google Document AIgoogle/document-ai | Florence-2microsoft/florence-2 | |
|---|---|---|
| Type | OCR API | Open source |
| Price | 10 credits / page | 1 credit / page |
| Per 1,000 pages | $10.00 | $1.00 |
| Typical speed | 1.4 s / page | 0.8 s / page |
| Best for | Multilingual scans | Lightweight OCR with boxes |
| Inputs | PDF, images | images |
| Languages | 200+ languages | English |
| Max pages per request | 500 | 500 |
| Tables | ✓ Yes | No |
| Handwriting | ✓ Yes | No |
| Math | No | No |
| 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 and drops to $0.60 above 5M pages a month, with the first 1,000 free.
- Layout Parser returns chunks for RAG at $10 per 1,000 pages, so you do not have to write your own chunking step.
- Batch requests accept up to 500 pages, and output includes JSON, plain text, bounding boxes and chunks.
Choose Florence-2 if
- It is MIT licensed and free to self-host, so you pay only for compute.
- At 0.23B (base) or 0.77B (large) parameters, it is small enough for lightweight edge OCR in English.
- OCR_WITH_REGION gives quadrilateral boxes per text line, and the same model also handles captioning, detection and grounding.
Key differences
| Google Document AI | Florence-2 | |
|---|---|---|
| How you run it | Hosted API on Google Cloud | Self-hosted via Transformers |
| Licence | Proprietary | MIT |
| Price | Enterprise Document OCR $1.50 per 1,000 pages ($0.60 above 5M/month); Layout Parser $10; Form Parser $30 | Free; you pay for compute |
| Output formats | JSON, plain text, bounding boxes, chunks | Plain text and bounding boxes only; no Markdown, tables or LaTeX |
| Page and size limits | Online requests up to 15 pages (30 in imageless mode); batch up to 500 pages; Form Parser batch up to 100 pages | Not published (model size: 0.23B base, 0.77B large) |
| Tables | 64.6% on RD-TableBench, behind Azure and Textract | No table output |
| Language and handwriting | Not published | Spelling errors and missing spaces on cursive handwriting and French text; Chinese output mostly wrong because the vocabulary lacks CJK characters |
Sources
- Document AI pricing
- Document AI limits
- Reducto RD-TableBench
- Florence-2-large model card
- HF discussion Chinese very bad
What each one is
Google Document AI
Google Cloud OCR with layout parsing and specialised processors.
Google Document AI detailsFlorence-2
Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.
Florence-2 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": ["microsoft/florence-2"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Google Document AI alternativesFlorence-2 alternativesBest OCR models in 2026