Academic paper OCR API
Convert research papers into clean Markdown with headings, equations, tables, figures and references in reading order.
Result
Your Markdown or JSON shows up here.
What makes academic papers hard to read
- Two-column layouts and reading order
- Inline and display equations
- Footnotes, figure captions and references
What you can pull out
academic-paper fields
{
"title": "Sparse Attention for Long Documents",
"authors[]": "name, affiliation",
"abstract": "We propose...",
"sections[]": "heading, markdown",
"equations": "LaTeX",
"tables[]": "caption, rows",
"references[]": "citation"
}Best models for academic papers
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 / page3Mathpix ConvertSpecialist for math, science papers and handwritten formulas. Outputs LaTeX.mathpix/convert7 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"
}'