OCRRouter

Qwen-VL vs Mistral Small 3.2

Mistral Small 3.2 is cheaper per page. Qwen-VL is faster. Only Qwen-VL supports Tables, Handwriting, Math, Bounding boxes.

Qwen-VLqwen/qwen-vlMistral Small 3.2mistral/mistral-small-3-2
TypeOpen sourceOpen source
Price2 credits / page1 credit / page
Per 1,000 pages$2.00$1.00
Typical speed2.0 s / page3.0 s / page
Best forFlexible extraction with promptsSelf-hosted small vision model
InputsPDF, imagesimages
Languages30+ languagesMultilingual
Max pages per request20050
Tables✓ YesNo
Handwriting✓ YesNo
Math✓ YesNo
Bounding boxes✓ YesNo
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

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL 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": "qwen/qwen-vl","fallbacks": ["mistral/mistral-small-3-2"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qwen-VL alternativesMistral Small 3.2 alternativesBest OCR models in 2026