AI Inference · x402 · early usage

Extract tabular data from messy text or HTML using Claude Haiku — detects columns and r…

Extract tabular data from messy text or HTML using Claude Haiku — detects columns and rows in unstructured content and returns clean structured JSON (columns + rows) so agents can turn pasted tables, HTML tables, and delimited text into usable data in one cal…

by netintel.dev · discovered, not yet claimed by its owner · updated 2026-10-08

30d calls2

30d payers2

MethodPOST

Outputjson

Mirrored from Coinbase's public x402 Bazaar. The description is the provider's own text and has not been reviewed here; the payment requirements are copied as published.

What it does

Tags: data extraction · document parsing · structured data · text to json · llm extraction · bazaar

Call contract

Method: POST
Input: json
Output: json
Last paid call: 2026-10-08

Input example from Bazaar metadata

{
  "text": "product | price | qty\nWidget A | 5.00 | 10\nWidget B | 7.50 | 4"
}

Output example

{
  "cached": false,
  "column_count": 3,
  "findings": [],
  "grade": "A",
  "score": 100,
  "table": {
    "columns": [
      "product",
      "price",
      "qty"
    ],
    "row_count": 2,
    "rows": [
      {
        "price": "5.00",
        "product": "Widget A",
        "qty": "10"
      },
      {
        "price": "7.50",
        "product": "Widget B",
        "qty": "4"
      }
    ]
  }
}

Use with an agent

Discover. Agents find this listing with GET https://bazaar.saylorinnovations.com/discovery/search?query=…, the MCP tool search_resources, or /discovery/resources.
Inspect. Fetch /resources/29576.json for the price and payment options.
Pay. Call GET https://netintel.dev/extract/table. The provider answers 402 with its payment requirements. An x402 client signs one of the options below and retries with PAYMENT-SIGNATURE.
Execute. The provider returns 200 with the data. Agent Bazaar is not in the request path and never sees your payment.

For humans

You don't need an account or an API key; you need a wallet holding a small amount of USDC on Base, Solana, and an x402-capable client (see the examples below). Call the endpoint unpaid first to see exactly what it asks for.

Pricing & payment

Price: $0.02 / request
Protocol: x402 v2
Auth: No account or API key. Pay per request.
Networks: Base, Solana
Demand: 2 calls · 2 unique payers in 30d (public x402 Bazaar data)

x402 payment requirements

Scheme	Network	Asset	Amount	Pay to	Timeout
exact	Base eip155:8453	USDC	$0.02	0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df	300s
exact	Solana solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp	USDC	$0.02	8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s	300s

accepts[] (raw JSON)

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0xdaDc335482AD545296Fd7b28518A251fFCbEb9Df",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "20000",
    "amountUsd": 0.02,
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
    "payTo": "8FVeybWnB4dYrxTuPK7WzFZNAiEcFVaDLFnKpRwVGr5s",
    "asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
    "amount": "20000",
    "amountUsd": 0.02,
    "maxTimeoutSeconds": 300
  }
]

Schemas

Output schema (JSON Schema)

{
  "properties": {
    "example": {
      "properties": {
        "cached": {
          "description": "True if served from the in-memory cache.",
          "type": "boolean"
        },
        "column_count": {
          "description": "Number of columns detected.",
          "type": "number"
        },
        "findings": {
          "description": "Informational findings (e.g. no_table_found, count_mismatch).",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "grade": {
          "description": "Letter grade A-F",
          "type": "string"
        },
        "score": {
          "description": "Quality score 0-100",
          "type": "number"
        },
        "table": {
          "description": "Parsed table: columns (array of column names), rows (array of objects keyed by column name), and row_count (number of rows). Empty columns/rows with row_count 0 when no tabular structure is detected.",
          "type": "object"
        }
      },
      "type": "object"
    },
    "type": {
      "type": "string"
    }
  },
  "required": [
    "type"
  ],
  "type": "object"
}

Example shape — generated from the schema, not a captured live response

{
  "example": {
    "cached": true,
    "column_count": 0,
    "findings": [
      "string"
    ],
    "grade": "string",
    "score": 0,
    "table": {}
  },
  "type": "string"
}

Examples

curl

curl -X POST 'https://netintel.dev/extract/table' -H 'Content-Type: application/json' --data '{"text":"product | price | qty\nWidget A | 5.00 | 10\nWidget B | 7.50 | 4"}'
# -> 402 Payment Required; read PAYMENT-REQUIRED
# retry the identical request with PAYMENT-SIGNATURE

JavaScript

const res = await fetch("https://netintel.dev/extract/table", {
  "method": "POST",
  "headers": {
    "content-type": "application/json"
  },
  "body": "{\"text\":\"product | price | qty\\nWidget A | 5.00 | 10\\nWidget B | 7.50 | 4\"}"
});
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

Python

import httpx
import json
res = httpx.request("POST", "https://netintel.dev/extract/table", json=json.loads("{\"text\":\"product | price | qty\\nWidget A | 5.00 | 10\\nWidget B | 7.50 | 4\"}"))
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header

Details

Provider: netintel.dev
Endpoint: https://netintel.dev/extract/table
Machine-readable: /resources/29576.json