OCRRouter

Pixtral vs Phi-3.5-vision

Phi-3.5-vision is cheaper per page.

Pixtralmistral/pixtralPhi-3.5-visionmicrosoft/phi-3-5-vision
TypeVision modelOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed3.0 s / page3.0 s / page
Best forQuestions about document imagesSmall self-hosted model
Inputsimagesimages
LanguagesMultilingualEnglish for vision
Max pages per request50050
TablesNoNo
HandwritingNoNo
MathNoNo
Bounding boxesNoNo
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

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 details

Phi-3.5-vision

Microsoft's 4.2B vision model (August 2024).

Phi-3.5-vision details

Try 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": ["microsoft/phi-3-5-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Pixtral alternativesPhi-3.5-vision alternativesBest OCR models in 2026