Newspaper OCR API
Read newspaper pages and archives into separate articles with headlines, bylines and body text in the right order.
結果
変換されたMarkdownやJSONがここに表示されます。
What makes newspapers hard to read
- Many columns and articles that jump between pages
- Faded microfilm and old print
- Ads mixed in with editorial text
What you can pull out
newspaper fields
{
"publication": "The Evening Courier",
"date": "1962-03-14",
"page": "3",
"articles[]": "headline, byline, body",
"ads_present": "true"
}Best models for newspapers
1Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.
google/gemini-flash3 credits / page2Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / page3Google Document AIGoogle Cloud OCR with layout parsing and specialised processors.google/document-ai3 credits / pageCall it from your code
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-flash",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'