Japanese OCR API
Read Japanese documents with kanji, kana and furigana, in horizontal or vertical layout.
Hasil
Markdown atau JSON anda akan dipaparkan di sini.
What makes Japanese hard for OCR
- Vertical text read right to left
- Furigana above kanji
- Three scripts plus Latin in one line
Script: Kanji, hiragana and katakana.
Call it from your code
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"
}'Best models for Japanese text
1PaddleOCR-VLOpen-source document model from Baidu. Excellent on Chinese, Japanese and Korean.
paddle/paddleocr-vl2 credits / page2Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.google/gemini-flash3 credits / page3Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / page