# Document Structured Extractor

> Document Structured Extractor is a paid API for AI agents from i3p3mgbsn54dvlivnk6wbumal40eqtsn.lambda-url.us-east-1.on.aws, paid per call via x402, $0.05/call, status unknown (last checked 2026-10-10).

Extracts structured fields and source evidence from documents (tenders, invoices, contracts, privacy policies) using task-specific profiles, returning schema-validated JSON with confidence scores and page references.

## Facts

- Endpoint: POST https://i3p3mgbsn54dvlivnk6wbumal40eqtsn.lambda-url.us-east-1.on.aws/v1/document-structured-extractor?utm_source=zero.xyz
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/document-structured-extractor-ebb82701
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5V331OJDffSIw1-pr7Q4d

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability document-structured-extractor-ebb82701 -d '<json body>'
```

Example prompt: Extract all the key structured fields from this invoice document using the invoice profile — I need the vendor name, line items, totals, and due date, along with confidence scores and which page each field came from.

## When to prefer this

Choose this endpoint when you need structured, schema-validated field extraction from business or legal documents with task-specific profiles (invoices, tenders, contracts, privacy policies) and require confidence scores and source page references for auditability. Prefer over generic extraction when you need profile-specific field sets and traceable evidence for each extracted value.

## Known failure modes

- Unsupported document profile type returns an error indicating valid profiles
- Low-confidence extractions may return null or partial field values
- Malformed or unreadable document text results in extraction failure
- Missing required document content causes incomplete schema output
- Very long documents may exceed processing limits

## How this service works

Extract structured fields and source evidence from supported documents using task-specific profiles such as tenders, invoices, contract dates, and privacy policies. Returns schema-validated JSON with confidence and page/source references.

## Output

A schema-validated JSON object containing extracted field values organized by document profile (tender, invoice, contract dates, or privacy policy), each field annotated with a confidence score (0–1) and page/source references indicating where in the document the value was found.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/document-structured-extractor-ebb82701/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from i3p3mgbsn54dvlivnk6wbumal40eqtsn.lambda-url.us-east-1.on.aws](https://www.zero.xyz/host/i3p3mgbsn54dvlivnk6wbumal40eqtsn.lambda-url.us-east-1.on.aws/llms.txt)