Florence-2 vs Mistral Medium 3
Florence-2 is cheaper per page. Florence-2 is faster. Only Florence-2 supports Bounding boxes. Only Mistral Medium 3 supports Tables, Math, Multilingual.
Florence-2microsoft/florence-2 | Mistral Medium 3mistral/mistral-medium-3 | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 4 credits / page |
| Per 1,000 pages | $1.00 | $4.00 |
| Typical speed | 0.8 s / page | 2.5 s / page |
| Best for | Lightweight OCR with boxes | Hosted general vision in the EU |
| Inputs | images | images |
| Languages | English | Multilingual |
| Max pages per request | 500 | 50 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| 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 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": ["mistral/mistral-medium-3"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Florence-2 vs Mistral Small 3.2Florence-2 vs Llama 3.2 11B VisionTesseract.js vs Mistral Medium 3Typhoon OCR vs Mistral Medium 3TrOCR vs Florence-2Qianfan OCR vs Florence-2Hunyuan OCR vs Florence-2Kraken vs Florence-2
Florence-2 alternativesMistral Medium 3 alternativesBest OCR models in 2026