# Pocket Network Table Extraction

> Pocket Network Table Extraction is a paid API for AI agents from agent.pocket.network, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-02).

Extracts structured tables from document text into typed JSON with headers, rows, and cell types, paid per-request in USDC with no API key required.

## Facts

- Endpoint: POST https://agent.pocket.network/v1/table-extraction?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/pocket-network-table-extraction-5c292c05
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_g7GfSh8V1PKsOWYlmKETe

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 pocket-network-table-extraction-5c292c05 -d '<json body>'
```

Example prompt: Can you extract all the tables from this text and give me back the headers, rows, and cell types as structured JSON? Here's the document: 'Product | Price | Qty\nWidgetA | $10.00 | 50\nWidgetB | $25.00 | 20'

## When to prefer this

Choose this endpoint when you need deterministic, structured extraction of tabular data from plain text — especially from document extracts, reports, or any text containing rows and columns. It is ideal for agentic workflows that need typed JSON (not raw string scraping) and where no API key or account setup is desired. Prefer it over general-purpose LLM parsing when consistency and cost predictability matter, and over OCR-based table tools when you already have the text content.

## Known failure modes

- Input text contains no recognizable tables — returns empty tables array
- Malformed or ambiguous table formatting may cause incorrect row/column alignment
- Very large documents may time out or produce truncated results
- Non-Latin character sets or complex nested tables may parse incorrectly
- Missing or empty 'text' field returns a validation error

## How this service works

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.

## Output

Returns a single JSON object containing all parsed tables found in the input text. Each table includes an array of headers (column names), an array of rows (each row being an array of cell values), and cell type annotations indicating the data type (string, number, currency, etc.) for each column or cell.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "Text to extract tables from."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {},
  "portal": {
   "serviceId": "table-extraction",
   "provenance": "third-party-supplier",
   "schemaCheck": "passed"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/pocket-network-table-extraction-5c292c05/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent.pocket.network](https://www.zero.xyz/host/agent.pocket.network/llms.txt)