Web

PDF → text API

Fetch a PDF by URL and extract its text + page count, so agents can read PDFs they otherwise can't parse. Answers 'extract text from this PDF', 'read this PDF', 'what does this PDF say', 'get the text of this document'. Text-based PDFs only (scanned/image PDFs need OCR).

Price$0.01per request

MethodPOST

Route/v1/web/pdf

StatusLive

MIME typeapplication/json

Rate limit30/minute

Cache86400s public

webpdftext-extractiondocumentparseocrreaderfiles

API URLhttps://x402.hexl.dev/v1/web/pdf

Integration docs

Example request

{
  "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
  "maxChars": 2000
}

Example response

{
  "url": "https://example.com/report.pdf",
  "pages": 12,
  "length": 48210,
  "truncated": true,
  "text": "Annual Report 2025\nRevenue grew 14%…"
}

Input schema

{
  "type": "object",
  "required": [
    "url"
  ],
  "properties": {
    "url": {
      "type": "string",
      "examples": [
        "https://example.com/doc.pdf"
      ]
    },
    "maxChars": {
      "type": "number",
      "default": 10000
    }
  }
}

Output schema

{
  "type": "object",
  "additionalProperties": true
}