Florence-2 vs LLaVA-OneVision
Florence-2 is faster. Only Florence-2 supports Bounding boxes. Only LLaVA-OneVision supports Multilingual.
Florence-2microsoft/florence-2 | LLaVA-OneVisionllava/llava-onevision | |
|---|---|---|
| Type | Open source | Open source |
| Price | 1 credit / page | 1 credit / page |
| Per 1,000 pages | $1.00 | $1.00 |
| Typical speed | 0.8 s / page | 3.0 s / page |
| Best for | Lightweight OCR with boxes | Open research vision model |
| Inputs | images | images |
| Languages | English | Mainly English |
| Max pages per request | 500 | 50 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | ✓ Yes | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | No | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
Florence-2
Small Microsoft vision model (0.23B and 0.77B) with OCR and OCR-with-regions tasks that return text with boxes.
Florence-2 detailsLLaVA-OneVision
Open vision model from the LLaVA project for single images, multiple images and video.
LLaVA-OneVision detailsTry both on your own file
Run the file once with each model and compare the output.
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
Use one, fall back to the other
{"model": "microsoft/florence-2","fallbacks": ["llava/llava-onevision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Florence-2 vs Aya VisionFlorence-2 vs Llama Nemotron Nano VLTesseract.js vs LLaVA-OneVisionTyphoon OCR vs LLaVA-OneVisionKraken vs Florence-2Jina OCR vs Florence-2Google Document AI vs Florence-2Tesseract vs Florence-2
Florence-2 alternativesLLaVA-OneVision alternativesBest OCR models in 2026