Mistral Small 3.2 vs Command A Vision
Mistral Small 3.2 is cheaper per page. Command A Vision is faster. Only Command A Vision supports Tables, Math.
Mistral Small 3.2mistral/mistral-small-3-2 | Command A Visioncohere/command-a-vision | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 1 credit / page | 4 credits / page |
| Per 1,000 pages | $1.00 | $4.00 |
| Typical speed | 3.0 s / page | 2.5 s / page |
| Best for | Self-hosted small vision model | Enterprise document questions |
| Inputs | images | images |
| Languages | Multilingual | Multilingual |
| Max pages per request | 50 | 50 |
| Tables | No | ✓ Yes |
| Handwriting | No | No |
| Math | No | ✓ Yes |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ 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
Command A Vision
Cohere's enterprise vision model (July 2025) for documents, charts and scans.
Command A Vision 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": "mistral/mistral-small-3-2","fallbacks": ["cohere/command-a-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Mistral Small 3.2 vs Janus-ProMistral Small 3.2 vs Aya VisionGrok 4 vs Command A VisionMistral Medium 3 vs Command A Vision
Mistral Small 3.2 alternativesCommand A Vision alternativesBest OCR models in 2026