Pixtralmistral/pixtral | Kimi-VL-A3Bmoonshot/kimi-vl | |
|---|---|---|
| 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 | Efficient self-hosted vision |
| Inputs | images | images |
| Languages | Multilingual | Mainly English and Chinese |
| 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 detailsKimi-VL-A3B
Moonshot's mixture-of-experts vision model with about 3B active parameters (April 2025).
Kimi-VL-A3B 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": ["moonshot/kimi-vl"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
Pixtral vs GLM-4.5VPixtral vs Phi-3.5-visionInternVL3.5 vs Kimi-VL-A3BRolmOCR vs Kimi-VL-A3BSmolDocling vs PixtralQianfan OCR vs PixtralGemini Flash vs PixtralRolmOCR vs Pixtral
Pixtral alternativesKimi-VL-A3B alternativesBest OCR models in 2026