QVQ-72B-Previewqwen/qvq-72b | Amazon Nova Liteamazon/nova-lite | |
|---|---|---|
| Type | Open source | Vision model |
| Price | 3 credits / page | 1 credit / page |
| Per 1,000 pages | $3.00 | $1.00 |
| Typical speed | 3.0 s / page | 3.0 s / page |
| Best for | Visual reasoning over charts | Cheap vision on AWS Bedrock |
| Inputs | images | PDF, images |
| Languages | Mainly English and Chinese | Multilingual |
| Max pages per request | 50 | 100 |
| Tables | No | No |
| Handwriting | No | No |
| Math | No | No |
| Bounding boxes | No | No |
| Confidence | No | No |
| Forms | No | No |
| Multilingual | ✓ Yes | ✓ Yes |
| On OCRRouter | Available | Available |
Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.
What each one is
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": ["amazon/nova-lite"],"file_url": "https://example.com/document.pdf"}Questions
More comparisons
QVQ-72B-Preview vs Phi-3.5-visionQVQ-72B-Preview vs Amazon Nova ProLlama 4 Maverick vs Amazon Nova LiteQwen-VL-Max vs Amazon Nova Lite
QVQ-72B-Preview alternativesAmazon Nova Lite alternativesBest OCR models in 2026