Book OCR API
Turn scanned books into clean, searchable text or Markdown, page by page, with headers and page numbers removed.
結果
変換されたMarkdownやJSONがここに表示されます。
What makes books hard to read
- Curved pages near the spine
- Running headers and page numbers mixed with body text
- Old typefaces, ligatures and hyphenation
What you can pull out
book fields
{
"title": "A History of the Harbour",
"page": "142",
"chapter": "Chapter 7: The Docks",
"text": "By the turn of the century...",
"footnotes[]": "text"
}Best models for books
1Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.
mistral/mistral-ocr6 credits / page2MarkerHosted version of the open-source Marker and Surya models. Strong on books and papers.datalab/marker14 credits / page3Gemini FlashGeneral vision model with strong handwriting and layout understanding at a low price.google/gemini-flash3 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": "mistral/mistral-ocr",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'