PDF to LLMs.txt

POST/api/ocr

Convert a PDF file to optimized LLM-ready text using OCR.

Content-Type: multipart/form-data

fileFilerequired

The PDF file to process

providerstringoptional

"mistral" (default) or "openai"

mistralmistral-ocr-latest • Native OCR

openaigpt-5.1 • Vision-based

Max file size50 MB

FormatsPDF

curl -X POST https://your-domain.com/api/ocr \
  -F "[email protected]" \
  -F "provider=mistral"

200

{
  "text": "# Document Title\n\nExtracted markdown...",
  "pageCount": 5,
  "filename": "document.pdf",
  "provider": "mistral"
}

4xx

{
  "error": "Only PDF files are supported"
}

textExtracted content as markdown

pageCountNumber of pages processed

filenameOriginal file name

providerOCR provider used