Contract OCR API
Convert long scanned contracts to clean Markdown with headings and clause numbering preserved, ready for review or search.
Result
Your Markdown or JSON shows up here.
What makes contracts hard to read
- Fifty-plus pages per file
- Nested clause numbering
- Signatures, stamps and handwritten edits
What you can pull out
contract fields
{
"parties[]": "Acme Pty Ltd, Beta LLC",
"effective_date": "2026-01-01",
"term": "24 months",
"governing_law": "New South Wales",
"clauses[]": "number, heading, text"
}Best models for contracts
1ClaudeGeneral vision model with careful reading of long, dense documents.
anthropic/claude14 credits / page2Reducto ParseHigh-accuracy parsing for complex financial and legal documents, with citations.reducto/parse20 credits / page3Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / pageCall it from your code
curl https://api.ocrrouter.com/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'