QVQ-72B-Preview OCR online
Qwen's experimental visual reasoning model (December 2024).
PDF, PNG, JPG, WebP, HEIC. Up to 10 files at onceNo file?
- Model ID
- qwen/qvq-72b
- Type
- Open source
- Price
- 3 credits / page ($3.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- images
- Languages
- Mainly English and Chinese
- Max pages per request
- 50
- Output
- Markdown, JSON
- License
- Qwen License
- Supports
- Multilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qvq-72b",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'QVQ-72B-Preview speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
QVQ-72B-Preview pricing
QVQ-72B-Preview costs 3 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $3.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 16 pages with this model. See pricing for credit packs.
Similar models
1Llama 3.2 90B VisionMeta's larger Llama 3.2 vision model (September 2024).3 credits / page
meta/llama-3-2-90b-vision3 credits / page2Gemma 3Google's open-weight model family (March 2025). The 4B, 12B and 27B sizes accept images.2 credits / pagegoogle/gemma-32 credits / page3Llama 3.2 11B VisionMeta's smaller Llama 3.2 vision model (September 2024).1 credit / pagemeta/llama-3-2-11b-vision1 credit / pageAll QVQ-72B-Preview alternativesBest OCR models by use case
Compare QVQ-72B-Preview
QVQ-72B-Preview vs Llama 3.2 90B VisionQVQ-72B-Preview vs Gemma 3QVQ-72B-Preview vs Llama 3.2 11B VisionQVQ-72B-Preview vs Doubao-Seed-1.6QVQ-72B-Preview vs ChandraQVQ-72B-Preview vs Azure Document Intelligence