# AgentTools HTML Table Extractor

> AgentTools HTML Table Extractor is a paid API for AI agents from agenttools-hub.vercel.app, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-02).

Extracts all HTML tables from a given URL or raw HTML string and returns them as structured JSON with headers and rows intact.

## Facts

- Endpoint: GET https://agenttools-hub.vercel.app/api/v1/dev/table-extract?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agenttools-html-table-extractor-a2aa5f70
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_gqA-HNHbs7HV21kuj17iz

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 agenttools-html-table-extractor-a2aa5f70
```

Example prompt: Can you extract all the tables from https://en.wikipedia.org/wiki/List_of_countries_by_GDP and give me the data as structured JSON rows and columns?

## When to prefer this

Choose this endpoint when you need to extract structured tabular data from a webpage or raw HTML without using a vision model or complex scraping pipeline. It is ideal for pricing tables, comparison charts, statistics tables, and any page where data is already structured in HTML table tags. Prefer this over general-purpose web scrapers when you specifically need table data as clean JSON rows and columns, and over vision models when the source is parseable HTML.

## Known failure modes

- URL is inaccessible or returns a non-200 status — no tables returned
- Page contains no HTML tables — returns empty array
- Malformed raw HTML provided — partial or empty extraction
- Limit parameter set too low — only first N tables returned
- Page requires JavaScript rendering — static HTML fetch may miss dynamically loaded tables
- Rate limiting or timeout on the target URL — extraction fails

## How this service works

Extract every HTML table from a page (or raw HTML) as structured JSON: headers and rows kept intact. The deterministic answer to 'get the pricing table / comparison table / stats table from this page' — no vision model needed. Use this when an agent needs to hTML tables → structured JSON rows and columns.

## Output

Returns a JSON array of tables found on the page, each containing a 'headers' array (column names) and a 'rows' array of arrays (cell values), preserving the original table structure. May also include table index and count of tables found.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [],
     "properties": {
      "url": {
       "type": "string",
       "description": "Or provide raw HTML instead"
      },
      "html": {
       "type": "string",
       "description": "Raw HTML"
      },
      "limit": {
       "type": "number",
       "description": "Max tables"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agenttools-html-table-extractor-a2aa5f70/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agenttools-hub.vercel.app](https://www.zero.xyz/host/agenttools-hub.vercel.app/llms.txt)