# Agent Data Toolkit – Extract Structured JSON from Text

> Agent Data Toolkit – Extract Structured JSON from Text is a paid API for AI agents from agent-data-toolkit.onrender.com, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-15).

Uses an LLM worker to extract structured JSON matching a caller-supplied schema from free-form text input.

## Facts

- Endpoint: POST https://agent-data-toolkit.onrender.com/extract
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-data-toolkit-extract-structured-json-from-text-8d394e77
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zSXoPWYaupbfxTUKvIZfW

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-toolkit-extract-structured-json-from-text-8d394e77 -d '<json body>'
```

Example prompt: Pull structured data from this paragraph into my schema — the schema has fields: name (string), date (string), amount (number), and currency (string). The text is: 'John Smith agreed to pay $1,250 USD on March 15th for the consulting services.'

## When to prefer this

Use this endpoint when you need to extract structured, schema-conformant JSON from unstructured or semi-structured text using LLM understanding, especially when the fields are semantically complex or not delimited by clear markers. Prefer over regex or rule-based parsing when the text is natural language and field boundaries are ambiguous. Pairs well with the sibling JSON validator endpoint to confirm output correctness.

## Known failure modes

- Text contains no information mappable to the schema — returns empty or null-filled JSON
- Schema is malformed or unparseable — returns an error response
- LLM worker fails to produce valid JSON — may return a raw text error or malformed JSON artifact
- Input text is too long for the LLM context window — truncation or error
- Payment not completed (x402) — request rejected before processing

## How this service works

Extract structured JSON matching a given schema from free-form text using an LLM worker.

## Output

A JSON object whose fields and types conform to the schema provided by the caller, with values populated by an LLM worker that read and interpreted the free-form input text. Missing fields may be null or omitted depending on what was inferrable from the text.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "method"
   ],
   "properties": {
    "body": {
     "type": "object",
     "required": [
      "text",
      "schema"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "string, free-form text (required)"
      },
      "schema": {
       "type": "object",
       "description": "object, JSON Schema describing what to extract (required)"
      },
      "instructions": {
       "type": "string",
       "description": "string, optional extra guidance"
      }
     }
    }
   }
  },
  "output": {
   "type": "object",
   "properties": {
    "example": {
     "type": "object",
     "required": [
      "ok",
      "data"
     ],
     "properties": {
      "ok": {
       "type": "boolean"
      },
      "data": {},
      "schema_error": {
       "type": "string"
      },
      "schema_valid": {
       "type": "boolean"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-data-toolkit-extract-structured-json-from-text-8d394e77/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-data-toolkit.onrender.com](https://www.zero.xyz/host/agent-data-toolkit.onrender.com/llms.txt)