OCRRouter

Llama 3.2 11B Vision vs Mistral Small 3.2

The two are close on paper, so test both on your own files.

Llama 3.2 11B Visionmeta/llama-3-2-11b-visionMistral Small 3.2mistral/mistral-small-3-2
TypeOpen sourceOpen source
Price1 credit / page1 credit / page
Per 1,000 pages$1.00$1.00
Typical speed3.0 s / page3.0 s / page
Best forLightweight self-hosted visionSelf-hosted small vision model
Inputsimagesimages
LanguagesEnglish for visionMultilingual
Max pages per request5050
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

Llama 3.2 11B Vision

Meta's smaller Llama 3.2 vision model (September 2024).

Llama 3.2 11B Vision details

Mistral Small 3.2

Open-weight 24B Mistral model with image input.

Mistral Small 3.2 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": "meta/llama-3-2-11b-vision","fallbacks": ["mistral/mistral-small-3-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Llama 3.2 11B Vision alternativesMistral Small 3.2 alternativesBest OCR models in 2026