Table OCR API
Pull tables out of PDFs and images with merged cells and multi-row headers intact, as Markdown or as rows.
Resultado
Seu Markdown ou JSON aparecerá aqui.
What makes tables hard to read
- Borderless tables
- Merged and spanning cells
- Tables that continue on the next page
What you can pull out
table fields
{
"rows[][]": "[[\"Item\",\"Qty\"],[\"A\",\"2\"]]",
"markdown": "| Item | Qty |",
"bbox": "[96, 260, 1144, 520]",
"page": "3"
}Best models for tables
1Reducto ParseHigh-accuracy parsing for complex financial and legal documents, with citations.
reducto/parse20 credits / page2Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.mistral/mistral-ocr6 credits / page3MarkerHosted version of the open-source Marker and Surya models. Strong on books and papers.datalab/marker14 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": "reducto/parse",
"file_url": "https://example.com/invoice.pdf",
"format": "json"
}'