Extract every value from your documents.
With the proof attached. Send a file and the shape you want back. Every field returns cited to the page it came from, or declared absent. Never guessed.
Your schema shapes the output.
One call. A file, the shape you want, and a switch for proof. What comes back is JSON in exactly that shape.
Send a file and a shape
A URL, or the id of a file you already uploaded. Then a JSON Schema, or the name of a saved action so the request is two fields long. Up to 100 documents fit in one call.
We read it first
Born-digital pages are read directly. Scans go through OCR. Recordings are transcribed. You never call parse yourself. Extract runs it on the way in.
Read each field for what it is
Mark a field as money, a date, a phone number, or an address. $1,234.56 comes back as 1234.56. A date comes back in ISO. A date nobody can settle, like 03/04/2026, comes back exactly as written instead of guessed into the wrong month.
Ground every field
Turn citations on and each value points at its page and the box on that page, or at a timecode in a recording. A field with no evidence comes back null, with an entry that says so.
Wait, or don't
The call holds for up to 120 seconds. A longer run comes back as a 202 with a run id, never as a timeout. Poll it, or let a webhook bring the result to you.
Clean data from any document.
You choose the fields. Extract fills them, whatever the file looked like when it arrived.
Invoices
PDF, Word, Excel, or a scan. Vendor, dates, line items, and totals. A list of ten line items comes back with the evidence for each one.
Contracts
Parties, renewal dates, notice periods. A term written across two clauses is cited at both, because that is where it lives.
Statements and ledgers
Ask for rows instead of one record and a twelve-page statement comes back as one row per transaction, each row cited.
Related files
An application and its bank statement, or a contract and its amendment. Send them together and get one record back, each value cited to the file it came from.
Every value shows where it came from.
A citation carries the file, the page, and the box on that page. The value you doubt takes one click to check. Checked in one glance. Never invented.
Northwind Supply Co.
Extracted fields
const run = await client.extract({
file: { url: "https://example.com/invoice-4471.pdf" },
schema: invoiceSchema,
citations: true, // off by default; ask for the evidence
});
// Every field is cited, or declared absent. Nothing in between.
for (const [field, cited] of Object.entries(run.output?.citations ?? {})) {
for (const c of cited) {
if (c.notFound) console.log(field, "not in the document");
else console.log(field, c.page, c.bbox, c.text, c.confidence);
}
}It never guesses.
Most extraction fails quietly, with a plausible number in the wrong field. These are the places Extract is built to fail loudly instead.
| What people assume | What happens | |
|---|---|---|
| Missing values | The model fills the gap with something that looks right. | A value that is not in the document comes back null, with a notFound entry beside it. Your code can tell absent from empty. |
| Unsupported values | If a field got filled, it must have come from somewhere. | A field filled without evidence gets a deterministic second pass. It either finds the citation or declares the value absent. Nothing is left in between. |
| Confidence | One score for the whole document, and a shrug. | Every citation is scored on its own, against the exact quote it points at. Turn on the judge and a second pass re-scores each value against that evidence. |
| Ambiguous formats | 03/04/2026 gets normalized to whichever month the model prefers. | When no reading can settle it, the value comes back exactly as written. A person decides, not a coin flip. |
Data you can prove, from the first call.
Point Extract at your worst document with citations on. Read what comes back, then open the page behind any value you doubt.