# boris-tools Structured Extraction

> boris-tools Structured Extraction is a paid API for AI agents from tools.borisinc.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Extracts structured data from content using LLM cognition, returning JSON output for specified schemas — paid per call via x402 (USDC on Base) with no account or API key required.

## Facts

- Endpoint: GET https://tools.borisinc.com/paid/extract
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/boris-tools-structured-extraction-b1c2d899
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ofgE1AH6LuIXpZPZKGTvP

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 boris-tools-structured-extraction-b1c2d899
```

Example prompt: Extract the following fields — company name, job title, salary range, and required skills — from this job posting text: 'Senior ML Engineer at Acme Corp, $180k–$220k, requires Python, PyTorch, and 5+ years of experience.'

## When to prefer this

Choose this endpoint when you need schema-driven structured extraction from unstructured text without setting up an account or managing API keys. It is ideal for agent pipelines that need pay-as-you-go LLM extraction at $0.01/call via USDC on Base (x402). Prefer it over heavyweight cloud NLP services when cost predictability, no-subscription access, and JSON output from freeform text are the priorities.

## Known failure modes

- Payment failure via x402 if wallet lacks sufficient USDC on Base
- Malformed or missing 'required'/'properties' parameters return error JSON
- LLM unable to find requested fields returns null or empty values for those fields
- Very long input content may be truncated or exceed context limits
- Network timeout on independent hardware under high load

## How this service works

LLM cognition for AI agents: web research with cited sources, summarisation, structured extraction. Every paid tool has a FREE capped sample at /sample/* - try it, then pay per call via x402 (USDC on Base) for the uncapped version. HTTP + MCP surfaces, same prices. No account, no API key. Independent hardware. Auth-then-capture: you are not charged if delivery fails.

## Output

A JSON object containing the extracted fields as specified by the input schema properties. Each requested field is populated with the value found in the source content, using LLM reasoning to locate and normalize the data even from unstructured or messy input.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "required": {
   "type": "string"
  },
  "properties": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/boris-tools-structured-extraction-b1c2d899/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tools.borisinc.com](https://www.zero.xyz/host/tools.borisinc.com/llms.txt)
