Structured Extraction

documents

Serving

Rule-based extraction of named fields from text; not a language model, it returns only what the text states. POST /v1/extract with {text, schema}: schema is a JSON Schema, a list of field names, or {fields: {name: regex}}. Built-in fields include email, phone, date, url, money and company; other fields come from "Label: value" lines. Pay per request in USDC; no account, no API key.

Endpoint: POST https://test.agent.pocket.network/v1/structured-extraction/v1/extract
Price per call: $0.005 USD
Networks payable on: Base Sepolia (eip155:84532)
Protocol: rest

Calling it

The first call returns 402 Payment Required with the terms. Sign for those terms and retry the same request with the payment attached.

Example request

A real, working call — the request the service card verifies against.

curl -X POST https://test.agent.pocket.network/v1/structured-extraction/v1/extract \
  -H 'content-type: application/json' \
  -d '{"text":"Contact: john@example.com","schema":["email"]}'

Example response

The response this call returned, captured 2026-09-25 15:53:30 UTC.

{
  "portal": {
    "provenance": "third-party-supplier",
    "serviceId": "structured-extraction",
    "schemaCheck": "unchecked"
  },
  "data": {
    "fields": {
      "email": "john@example.com"
    },
    "matched_by": {
      "email": "builtin:email"
    },
    "deterministic": true,
    "schema_mode": "field_names",
    "service": "structured-extraction"
  }
}

Try it

Make one real paid call from your own wallet — about $0.005 on Base Sepolia (eip155:84532). The wallet signs; nothing here holds a key. You'll see exactly what the service answers.

No browser wallet found. Install MetaMask, Rabby, or Coinbase Wallet to try a call here.

EndpointRequest body

Supported methods

Methods the registry lists for this service. The portal forwards any call as sent; the supplier decides what it answers, and a delivered answer is settled.

Methods Structured Extraction accepts, and whether each reads or writes.
Method	Effect
`GET /v1/health`	read
`GET /v1/version`	read
`POST /v1/extract`	read

Schemas

Published by the service itself. The example above is generated from these.

Request schema

{
  "type": "object",
  "description": "The request body for POST /v1/extract.",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to extract from."
    },
    "schema": {
      "description": "A JSON Schema with properties, a list of field names, or {fields: {name: regex}}."
    }
  },
  "required": [
    "text",
    "schema"
  ]
}

Response schema

{
  "type": "object",
  "description": "For POST /v1/extract, a JSON object with `fields` (null when not found), matched_by and schema_mode. The exact shape is the service's own and is not pinned here; errors return a JSON object with an `error` field."
}