Pixtralmistral/pixtral | Llama 3.2 90B Visionmeta/llama-3-2-90b-vision | |
|---|---|---|
| Type | Vision model | Open source |
| Price | 2 credits / page | 3 credits / page |
| Per 1,000 pages | $2.00 | $3.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Questions about document images | Self-hosted image questions |
| Inputs | images | images |
| Languages | Multilingual | English for vision |
| 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 detailsLlama 3.2 90B Vision
Meta's larger Llama 3.2 vision model (September 2024).
Llama 3.2 90B 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/pixtral","fallbacks": ["meta/llama-3-2-90b-vision"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Pixtral vs Llama 3.2 11B VisionPixtral vs Llama 4 ScoutInternVL3.5 vs Llama 3.2 90B VisionRolmOCR vs Llama 3.2 90B VisionDocling vs PixtralOpenOCR vs PixtralPixtral vs InternVL3.5Pixtral vs Unstructured
Pixtral alternativesLlama 3.2 90B Vision alternativesBest OCR models in 2026