OCRRouter

Gemma 3 vs Qwen2.5-VL-72B

Gemma 3 is cheaper per page. Qwen2.5-VL-72B is faster. Only Qwen2.5-VL-72B supports Tables, Handwriting, Math, Bounding boxes.

Gemma 3google/gemma-3Qwen2.5-VL-72Bqwen/qwen2-5-vl-72b
TypeOpen sourceOpen source
Price2 credits / page3 credits / page
Per 1,000 pages$2.00$3.00
Typical speed3.0 s / page2.5 s / page
Best forSelf-hosted image readingSelf-hosted document parsing
InputsimagesPDF, images
Languages140+ languagesMultilingual
Max pages per request50100
TablesNo✓ Yes
HandwritingNo✓ Yes
MathNo✓ Yes
Bounding boxesNo✓ Yes
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

Gemma 3

Google's open-weight model family (March 2025). The 4B, 12B and 27B sizes accept images.

Gemma 3 details

Qwen2.5-VL-72B

Largest Qwen2.5-VL model (January 2025), strong on documents, charts and grounding.

Qwen2.5-VL-72B 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": "google/gemma-3","fallbacks": ["qwen/qwen2-5-vl-72b"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Gemma 3 alternativesQwen2.5-VL-72B alternativesBest OCR models in 2026