Qwen-VL OCR online
Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.
Qwen-VL versions: Qwen3-VL (September and October 2025), Qwen2.5-VL (January 28, 2025 (32B in March 2025)), Qwen2-VL (August 29, 2024)
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- qwen/qwen-vl
- Type
- Open source
- Price
- 2 credits / page ($2.00 per 1,000 pages)
- Typical speed
- 2.0 s / page
- Inputs
- PDF, images
- Languages
- 30+ languages
- Max pages per request
- 200
- Output
- Markdown, JSON with positions
- Supports
- TablesHandwritingMathBounding boxesMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen-vl",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'Qwen-VL speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
Qwen-VL pricing
Qwen-VL costs 2 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $2.00. You only pay for pages that return a result.
New accounts get 50 free credits, enough for about 25 pages with this model. See pricing for credit packs.
Similar models
1Qwen3-VLAlibaba's Qwen3 vision-language family (2025), with expanded OCR language support.
qwen/qwen3-vl2 credits / page2Qwen2.5-VL-7B7B Qwen2.5-VL model that fits on a single GPU.qwen/qwen2-5-vl-7b1 credit / page3Qwen2.5-VL-72BLargest Qwen2.5-VL model (January 2025), strong on documents, charts and grounding.qwen/qwen2-5-vl-72b3 credits / pageAll Qwen-VL alternativesBest OCR models by use case
Compare Qwen-VL
Qwen-VL vs Qwen3-VLQwen-VL vs Qwen2.5-VL-7BQwen-VL vs Qwen2.5-VL-72BQwen-VL vs ChunkrQwen-VL vs LlamaParseQwen-VL vs Molmo