OCRRouter

Marker vs Llama 3.2 90B Vision

Llama 3.2 90B Vision is cheaper per page. Marker is faster. Only Marker supports Tables, Math, Bounding boxes.

Markerdatalab/markerLlama 3.2 90B Visionmeta/llama-3-2-90b-vision
TypeOCR APIOpen source
Price14 credits / page3 credits / page
Per 1,000 pages$14.00$3.00
Typical speed2.5 s / page3.0 s / page
Best forBooks and research papersSelf-hosted image questions
InputsPDF, images, DOCXimages
Languages90+ languagesEnglish for vision
Max pages per request1,00050
Tables✓ YesNo
HandwritingNoNo
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

Marker

Hosted version of the open-source Marker and Surya models. Strong on books and papers.

Marker 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": "datalab/marker","fallbacks": ["meta/llama-3-2-90b-vision"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Marker alternativesLlama 3.2 90B Vision alternativesBest OCR models in 2026