# Vextorium Language Detection

> Vextorium Language Detection is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-16).

Detects the language of a text using a statistical model (no AI), returning the detected language code, name, probability score, and alternative candidates across 55 languages.

## Facts

- Endpoint: POST https://api.vextorium.com/idioma-texto-pago?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-language-detection-82c4b6a9
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_86PMTqj7sW7f0TB6s41O7

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-language-detection-82c4b6a9 -d '<json body>'
```

Example prompt: What language is this text written in: 'Bonjour, je voudrais réserver une table pour deux personnes ce soir'? Give me the language code, name, and how confident you are.

## When to prefer this

Choose this endpoint when you need fast, cheap, non-AI language detection for routing or preprocessing — especially when you're calling at scale and don't need deep semantic understanding. Ideal over AI-based NLP services when cost matters ($0.003/call), latency must be minimal, and the 55-language statistical model is sufficient. Prefer it over translation APIs that include language detection as a side effect, when you only need the language identity without translating the content.

## Known failure modes

- Very short text (< 10 chars) may return low-confidence or unreliable results
- Mixed-language text may produce unexpected top-language selection
- Rare or minority languages not among the 55 supported may misclassify to a similar language
- Empty 'texto' field returns a validation error
- Ambiguous text (e.g. proper nouns, URLs only) may yield fiable:false with low probability

## How this service works

Detect the language of a text without AI (55 languages, statistical langdetect model) with probability and alternatives. Fast and cheap for routing messages or choosing a translation.

## Output

Returns a JSON object with: 'idioma' (ISO 639-1 language code, e.g. 'es'), 'nombre' (human-readable language name, e.g. 'español'), 'probabilidad' (confidence score 0–1), 'fiable' (boolean reliability flag), and 'alternativas' (array of alternative language candidates with their own scores).

## Request schema (JSON Schema)

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

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "fiable": true,
  "idioma": "es",
  "nombre": "español",
  "alternativas": [],
  "probabilidad": 1
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-language-detection-82c4b6a9/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)