# Vextorium Text Extract Numbers

> Vextorium Text Extract Numbers is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-15).

Extracts all numbers, monetary amounts, and percentages from a text string, parsing and normalizing them into structured values with currency detection and per-currency sums.

## Facts

- Endpoint: POST https://api.vextorium.com/v1/text-extract-numbers?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-text-extract-numbers-8cd0d367
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-gmiVBTP1-Ohqc8LRj0TN

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-text-extract-numbers-8cd0d367 -d '<json body>'
```

Example prompt: Extract all the numbers, monetary amounts, and percentages from this text and group the totals by currency: 'The fund raised $1,234.56 million, received 250 USDC, and returned 15% to investors.'

## When to prefer this

Use this endpoint when you need to extract and normalize all numeric data (amounts, percentages, plain numbers) from unstructured text in one call, especially when the text contains multiple currencies or mixed decimal formats. It is the right choice over regex-based solutions when you need currency detection, automatic decimal separator inference, and per-currency aggregation simultaneously. Prefer it over general NLP APIs when you specifically need structured numeric extraction with financial awareness.

## Known failure modes

- Missing required 'text' field in body returns a validation error
- Ambiguous decimal separators (when 'auto' cannot determine format) may produce incorrect parsed values
- Text with no recognizable numbers returns empty arrays and null sums
- Very long text inputs may time out or hit size limits
- Non-standard currency symbols may not be recognized and could be omitted from sum_per_currency

## How this service works

Extract and normalize every number in a text: amounts with currency (€, $, USDC, BTC...), percentages, multipliers (k, million, bn) and plain figures, understanding both 1.234,56 and 1,234.56, with totals per currency.

## Output

A JSON object containing: an 'amounts' array (each with the original text, parsed numeric value, and currency code), a 'numbers' array of plain numeric values, a 'percentages' array (each with original text and value), a 'sum_per_currency' object aggregating totals by currency code, and the detected 'decimal_separator'.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string"
  },
  "decimal": {
   "enum": [
    "auto",
    ",",
    "."
   ],
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "amounts": [
   {
    "text": "$1,234.56 million",
    "value": 1234560000,
    "currency": "USD"
   },
   {
    "text": "250 USDC",
    "value": 250,
    "currency": "USDC"
   }
  ],
  "numbers": [],
  "percentages": [
   {
    "text": "15%",
    "value": 15
   }
  ],
  "sum_per_currency": {
   "BTC": 0.05,
   "USD": 1234560000,
   "USDC": 250
  },
  "decimal_separator": "."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-text-extract-numbers-8cd0d367/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)