OCRRouter

PaddleOCR-VL online

Open-source document model from Baidu. Excellent on Chinese, Japanese and Korean.

PaddleOCR-VL versions: PaddleOCR-VL 1.5 (January 29, 2026)

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?
Model ID
paddle/paddleocr-vl
Type
Open source
Price
6 credits / page ($6.00 per 1,000 pages)
Typical speed
1.3 s / page
Inputs
PDF, images
Languages
109 languages
Max pages per request
500
Output
Markdown, JSON with positions
License
Apache-2.0
Supports
TablesMathBounding boxesConfidenceMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
  -H "Authorization: Bearer $OCRROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "paddle/paddleocr-vl",
    "file_url": "https://example.com/invoice.pdf",
    "format": "markdown"
  }'

PaddleOCR-VL speed and reliability

Loading…

Measured on our own traffic over the last 7 days.

PaddleOCR-VL pricing

PaddleOCR-VL costs 6 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $6.00. You only pay for pages that return a result.

New accounts get 50 free credits, enough for about 8 pages with this model. See pricing for credit packs.

Similar models

All PaddleOCR-VL alternativesBest OCR models by use case

Compare PaddleOCR-VL

PaddleOCR-VL versions

Questions