# Agent Data Tools: Extract JSON Fields from Text

> Agent Data Tools: Extract JSON Fields from Text is a paid API for AI agents from agent-data-tools.revmesh2074.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-30).

Extracts specific named fields from unstructured text and returns them as a structured JSON object using an LLM

## Facts

- Endpoint: GET https://agent-data-tools.revmesh2074.workers.dev/ai/extract-json?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-tools-extract-json-fields-from-text-eec9030d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Spu_uLMUoEzU-bRc_5_AN

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 agent-data-tools-extract-json-fields-from-text-eec9030d
```

Example prompt: Can you pull out the invoice number, company name, total amount, currency, and due date from this invoice text: 'Invoice #1043 from Acme AB, dated Oct 1 2026. Total due: 2,450 SEK by November 1, 2026.'

## When to prefer this

Use this endpoint when you need to extract a specific, named set of fields from unstructured or semi-structured text (invoices, contracts, emails, documents) and want a structured JSON response. It is ideal for document automation, data entry pipelines, and any scenario where you already know the field names you need. Prefer this over generic LLM calls when you want a lightweight, pay-per-call approach with no API key or account setup, and when the source text fits within 12,000 characters.

## Known failure modes

- Text exceeds 12,000 character limit — truncated or rejected input
- More than 30 fields requested — validation error
- Field names are ambiguous or not present in text — fields appear in 'missing' array
- LLM hallucination — field values may be inaccurate if text is unclear
- GET request with missing required query params (text or fields) — 400 error
- Payment failure — call not charged if x402 payment fails

## How this service works

Pull named fields out of unstructured text (emails, invoices, listings, bios) and get them back as a JSON object, with null for anything not present. Use to turn messy text into structured data for an agent.

## Output

Returns a JSON object with a 'data' key containing the extracted field values keyed by the requested field names, a 'model' string identifying the LLM used, and a 'missing' array listing any fields that could not be found in the source text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "text",
  "fields"
 ],
 "properties": {
  "text": {
   "type": "string",
   "description": "Source text, up to 12,000 characters"
  },
  "fields": {
   "type": "string",
   "description": "Comma-separated field names to extract (1-30)"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "data": {
   "type": "object",
   "properties": {
    "total": {
     "type": "number"
    },
    "company": {
     "type": "string"
    },
    "currency": {
     "type": "string"
    },
    "due_date": {
     "type": "string"
    },
    "invoice_number": {
     "type": "string"
    }
   }
  },
  "model": {
   "type": "string"
  },
  "missing": {
   "type": "array",
   "items": {}
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-tools-extract-json-fields-from-text-eec9030d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-tools.revmesh2074.workers.dev](https://www.zero.xyz/host/agent-data-tools.revmesh2074.workers.dev/llms.txt)