PDF to JSON

Send a PDF URL and a JSON schema; get the fields back as JSON. Tables and multi-column layouts included.

POST https://api.bottrunk.com/s/pdf-extract

Call it

# Ask. You get a 402 with the payment requirements.
curl https://api.bottrunk.com/s/pdf-extract \
  -d '{"url": "https://example.com/pricing"}'

# Pay and retry. Any x402 client does this for you.
curl https://api.bottrunk.com/s/pdf-extract \
  -H "X-PAYMENT: <signed USDC transfer>" \
  -d '{"url": "https://example.com/pricing"}'

from x402.clients import requests as x402_requests

session = x402_requests.x402_http_adapter(account)
r = session.post(
    "https://api.bottrunk.com/s/pdf-extract",
    json={"url": "https://example.com/pricing"},
)
print(r.json()["markdown"])

{ "mcpServers": { "bottrunk": { "url": "https://mcp.bottrunk.com" } } }
# then call the tool `pdf_extract` from your agent

Input

url	string	Public URL of the PDF.
schema	object	JSON schema of the fields to extract.

Output

data	object	Extracted fields, matching the schema.
pages	integer	Pages processed.