Extract data from a document: invoice, receipt, contract fields as JSON

$0.03 per call · failed calls are never charged · no account needed: a card key or USDC

Extract named fields from a document as JSON: give a PDF, Word, Excel or PowerPoint file, a scan or a photo (PNG, JPEG, WebP) by URL or in a POST body (up to 10 MB; images 3 MB) and the field names you want, such as invoice_number, total, due_date. An AI model reads the file, scans by OCR, and returns one JSON object, with null where a value is not stated. Use to turn invoices, receipts, orders and contracts into rows.

Run it free (3 free calls) Buy credits by card (from $1) Example result (JSON)

Try it with your own inputs

Absolute public http(s) URL of the file (or send the file in a POST body instead)
Comma-separated field names to extract (1-30)

Uses one of your 3 free calls. Nothing is charged, and a call that fails is not counted.

Inputs

NameTypeDescription
url (required)stringAbsolute public http(s) URL of the file (or send the file in a POST body instead)
fields (required)stringComma-separated field names to extract (1-30)

Request

Over HTTP, with a card key from /credits:

curl -H "Authorization: Bearer adt_…" "https://agent-data-tools.revmesh2074.workers.dev/document/extract?url=https%3A%2F%2Fcalibre-ebook.com%2Fdownloads%2Fdemos%2Fdemo.docx&fields=title%2Cebook_formats%2Cpens_needed%2Cscissors_needed"

Or one of your 3 free calls, no key:

curl "https://agent-data-tools.revmesh2074.workers.dev/document/extract?url=https%3A%2F%2Fcalibre-ebook.com%2Fdownloads%2Fdemos%2Fdemo.docx&fields=title%2Cebook_formats%2Cpens_needed%2Cscissors_needed&trial=1"

Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.

Example result

{
  "url": "https://calibre-ebook.com/downloads/demos/demo.docx",
  "type": "docx",
  "data": {
    "title": "Demonstration of DOCX support in calibre",
    "ebook_formats": [
      "EPUB",
      "AZW3"
    ],
    "pens_needed": 3,
    "scissors_needed": 1
  },
  "missing": [],
  "model": "@cf/meta/llama-4-scout-17b-16e-instruct",
  "charsRead": 8934,
  "truncated": false
}

From an AI agent (MCP)

Add the MCP server to Claude, Cursor or any MCP client. This tool is document_extract, and the first 25 successful calls are free:

https://agent-data-tools.revmesh2074.workers.dev/mcp

Related tools