Overview

DOCUMENT
INTELLIGENCE
BUILT IN.

The extraction layer for products that read documents. Your users upload a file — a trade license, an invoice, a passport — and your app receives structured data in seconds. One API. Any field. No pipeline to maintain.

01 · setup
02 · approve
03 · connect
04 · extract
Extraction

Your users upload.
Your app receives data.

Crooked phone shot, blurry scan, 12-page PDF — same API call. Docex handles orientation, OCR, retries, and schema validation so your product doesn't have to.

Trade License · Mainland
LegalACME LOGISTICS L.L.C
License1019388
Issued14·03·2024
Expires13·03·2026
ActivityFreight forwarding
IMG_4128.HEICiPhone 15
await docex.extract({
  file: "./uploaded-license.heic",
  prompt: "company name, number, expiry",
});

// → 200 OK · 2.4s · $0.05
{
  "legal_name": "ACME LOGISTICS L.L.C",
  "license_no": "1019388",
  "expires_on": "2026-03-13"
}
Inputs

Any document.
Any field.

Describe what you need. Docex reads the rest.

INV

Invoices

Line items, totals, tax, vendor, due dates

LIC

Trade Licenses

Legal name, number, expiry, activity

ID

IDs & Passports

Name, number, nationality, dates

RCT

Receipts

Merchant, amount, date, category

CTR

Contracts

Parties, terms, clauses, signatures

KYC

Bank Statements

Balance, transactions, account details

Billing

Predictable cost,
no procurement cycle.

Billed at 2× upstream cost. Drop in five dollars, extract about a hundred pages, and keep going. No annual commit, no sales call, no pricing spreadsheet. Infrastructure pricing for product teams.

  • Billed at 2× upstream cost
  • $5 minimum top-up
  • Mock provider for CI — $0
  • Cancel anytime, no lock-in
Wallet · acme-prod ● Active
$3.18 ≈ 64 pages
$5.00last top-up
$1.82spent this week
upstream cost
Initiate

Plug it in.
Ship the feature.

Paste this into your coding agent. It wires Docex into your product, scaffolds the endpoint, and runs a smoke test. You approve one link. Five minutes to production-ready extraction.

prompt.txt — copy & paste ⧉ copy
Wire Docex into this project as the document extraction layer for
[describe the use case — e.g., "reading trade licenses during user onboarding"].

Take me through the GitHub approval and the $5 wallet top-up, store the
API key in my env, scaffold a server-side extraction endpoint for my
stack, and run a smoke test to confirm the integration works end-to-end.