DeepSeek-VL2 OCR online
DeepSeek's mixture-of-experts vision models (December 2024) with OCR and table and chart understanding.
PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
- Model ID
- deepseek/deepseek-vl2
- Type
- Vision model
- Price
- 2 credits / page ($2.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- images
- Languages
- Mainly English and Chinese
- Max pages per request
- 500
- Output
- Markdown, JSON with positions
- License
- Code: MIT. Weights: DeepSeek Model License, commercial use allowed
- Supports
- TablesBounding boxes
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-vl2",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'DeepSeek-VL2 speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
DeepSeek-VL2 pricing
DeepSeek-VL2 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
1DoclingIBM's open-source document converter with a structured document model.
ibm/docling2 credits / page2SuryaOpen-source OCR toolkit with line detection, layout analysis, reading order and tables.datalab/surya2 credits / page3MonkeyOCROpen-source document parser that splits work into structure, recognition and relation steps.monkeyocr/monkeyocr2 credits / pageAll DeepSeek-VL2 alternativesBest OCR models by use case
Compare DeepSeek-VL2
DeepSeek-VL2 vs DoclingDeepSeek-VL2 vs SuryaDeepSeek-VL2 vs MonkeyOCRDeepSeek-VL2 vs Google Cloud Vision OCRDeepSeek-VL2 vs GPTDeepSeek-VL2 vs o4-mini