OCRRouter

QVQ-72B-Preview vs Llama 3.2 90B Vision

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

QVQ-72B-Previewqwen/qvq-72bLlama 3.2 90B Visionmeta/llama-3-2-90b-vision
TypeOpen sourceOpen source
Price3 credits / page3 credits / page
Per 1,000 pages$3.00$3.00
Typical speed3.0 s / page3.0 s / page
Best forVisual reasoning over chartsSelf-hosted image questions
Inputsimagesimages
LanguagesMainly English and ChineseEnglish for vision
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

QVQ-72B-Preview

Qwen's experimental visual reasoning model (December 2024).

QVQ-72B-Preview details

Llama 3.2 90B Vision

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

Llama 3.2 90B 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": "qwen/qvq-72b","fallbacks": ["meta/llama-3-2-90b-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

QVQ-72B-Preview alternativesLlama 3.2 90B Vision alternativesBest OCR models in 2026