Pixtralmistral/pixtral | SmolVLMhuggingface/smolvlm | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 2 credits / page | 1 credit / page |
| Per 1,000 pages | $2.00 | $1.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Questions about document images | On-device and edge use |
| Inputs | images | images |
| Languages | Multilingual | Mainly English |
| Max pages per request | 500 | 50 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| 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
Pixtral
Mistral's open-weight vision models, Pixtral 12B and Pixtral Large. Mistral's API no longer serves them, so they run self-hosted.
Pixtral 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/pixtral","fallbacks": ["huggingface/smolvlm"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Pixtral vs Idefics3Pixtral vs Doubao-Seed-1.6InternVL3.5 vs SmolVLMRolmOCR vs SmolVLMGoogle Document AI vs PixtralPixtral vs InternVL3.5Typhoon OCR vs PixtralTrOCR vs Pixtral
Pixtral alternativesSmolVLM alternativesBest OCR models in 2026