Donut vs Mistral Medium 3
Donut is cheaper per page. Donut is faster. Only Donut supports Forms. Only Mistral Medium 3 supports Tables, Math, Multilingual.
Donutnaver/donut | 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 | 1.0 s / page | 2.5 s / page |
| Best for | Receipt and form fields after fine-tuning | Hosted general vision in the EU |
| Inputs | images | images |
| Languages | English, Chinese, Japanese, Korean | Multilingual |
| Max pages per request | 100 | 50 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | ✓ Yes | 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
Donut
OCR-free document understanding model. Fine-tuned for receipts, forms and document Q&A.
Donut 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": "naver/donut","fallbacks": ["mistral/mistral-medium-3"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Donut vs Mistral Small 3.2Donut vs Llama 3.2 11B VisionGOT-OCR 2.0 vs Mistral Medium 3Nougat vs Mistral Medium 3Donut vs MiniCPM-V 4.5Donut vs RolmOCRMinerU vs DonutDonut vs DeepSeek-VL2
Donut alternativesMistral Medium 3 alternativesBest OCR models in 2026