Agentic Portal

Table Extraction from Text

documents
Serving

Extract tables from documents into typed JSON: headers, rows, and cell types. POST /v1/table with {text} and get the parsed tables as one JSON object. Deterministic on clean inputs. Pay per request in USDC; no account, no API key.

Endpoint
POST https://agent.pocket.network/v1/table-extraction
Price per call
$0.005 USD
Networks payable on
Base (eip155:8453)
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

Derived from the published request schema.

curl -X POST https://agent.pocket.network/v1/table-extraction \
  -H 'content-type: application/json' \
  -d '{"text":"string"}'
Example response

This service declares its response shape in prose rather than as fields, so there is nothing more specific to sample.

{}

Try it

Make one real paid call from your own wallet — about $0.005 on Base (eip155:8453). 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.

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 Table Extraction from Text accepts, and whether each reads or writes.
MethodEffect
GET /v1/healthread
GET /v1/versionread
POST /v1/tableread

Schemas

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

Request schema
{
  "type": "object",
  "description": "Document text containing one or more tables.",
  "properties": {
    "text": {
      "type": "string",
      "description": "Text to extract tables from."
    }
  },
  "required": [
    "text"
  ]
}
Response schema
{
  "type": "object",
  "description": "For POST /v1/table, a JSON object with a `tables` array of typed tables (headers, rows, cell types). The exact shape is the service's own and is not pinned here; errors return a JSON object with an `error` field, and the GET routes return their own small JSON documents."
}

Request body used in the example: { "text": "string" }