OCRRouter

Llama 3.2 90B Vision vs SmolVLM

SmolVLM is cheaper per page.

Llama 3.2 90B Visionmeta/llama-3-2-90b-visionSmolVLMhuggingface/smolvlm
TypeOpen sourceOpen source
Price3 credits / page1 credit / page
Per 1,000 pages$3.00$1.00
Typical speed3.0 s / page3.0 s / page
Best forSelf-hosted image questionsOn-device and edge use
Inputsimagesimages
LanguagesEnglish for visionMainly English
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 90B Vision

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

Llama 3.2 90B Vision details

SmolVLM

Hugging Face's small open vision models (256M to 2.2B).

SmolVLM 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-3-2-90b-vision","fallbacks": ["huggingface/smolvlm"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Llama 3.2 90B Vision alternativesSmolVLM alternativesBest OCR models in 2026