# Vextorium Extract Structured Data

> Vextorium Extract Structured Data is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.008/call, status unknown (last checked 2026-10-12).

Uses a local AI model to extract specific named fields from unstructured text such as invoices, emails, or messages, returning structured key-value pairs.

## Facts

- Endpoint: POST https://api.vextorium.com/v1/extract-structured-data?utm_source=zero.xyz
- Price: $0.008/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-extract-structured-data-0095d7a1
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Txfc77vFAEUoS5D7Eovdv

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 vextorium-extract-structured-data-0095d7a1 -d '<json body>'
```

Example prompt: Extract the invoice number, date, company name, amount, and currency from this text: 'Invoice 2026-117 issued by Acme SL on 12/09/2026 for EUR 1,250.50 for consulting services.'

## When to prefer this

Choose this endpoint when you need to pull specific named fields from unstructured text documents like invoices, emails, contracts, or messages and want structured JSON output. It is particularly well-suited for document automation pipelines where the field names are known in advance. Prefer it over generic LLM prompting when you want a consistent, schema-driven extraction result with a field-found count, and when paying per-call via x402 USDC micropayments is acceptable.

## Known failure modes

- Requested fields not present in source text return null values
- Ambiguous or poorly formatted text may result in incorrect field extraction
- Very short or context-free text may yield low found_fields count
- Fields with multiple candidates in text may return only one match
- Non-standard date or number formats may be returned as-is without normalization

## How this service works

517 pay-per-call data APIs for AI agents: Solana and EVM on-chain data, tokenized stocks, DeFi, Hyperliquid, economy and official statistics, FX, validation, web and developer tools. Pay in USDC via x402.

## Output

Returns a JSON object with a 'data' field containing the extracted key-value pairs for each requested field (null if not found), the local AI model used (e.g. Qwen3-8B), and a 'found_fields' count indicating how many fields were successfully extracted.

## 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",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "required": [
      "text",
      "fields"
     ],
     "properties": {
      "text": {
       "type": "string",
       "description": "Source text (invoice, email, message...)"
      },
      "fields": {
       "type": "array",
       "items": {
        "type": "string"
       },
       "description": "Field names to extract"
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": [
      "object",
      "null"
     ],
     "properties": {
      "data": {
       "type": [
        "object",
        "null"
       ],
       "properties": {
        "date": {
         "type": [
          "string",
          "null"
         ]
        },
        "amount": {
         "type": [
          "string",
          "null"
         ]
        },
        "company": {
         "type": [
          "string",
          "null"
         ]
        },
        "currency": {
         "type": [
          "string",
          "null"
         ]
        },
        "invoice_number": {
         "type": [
          "string",
          "null"
         ]
        }
       }
      },
      "model": {
       "type": [
        "string",
        "null"
       ]
      },
      "found_fields": {
       "type": [
        "number",
        "null"
       ]
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "date": "12/09/2026",
   "amount": "1.250,50",
   "company": "Acme SL",
   "currency": "EUR",
   "invoice_number": "2026-117"
  },
  "model": "Qwen3-8B (local)",
  "found_fields": 5
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-extract-structured-data-0095d7a1/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.vextorium.com](https://www.zero.xyz/host/api.vextorium.com/llms.txt)