# 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 2026-10-19).

Detects the language of a given text using a statistical model (no AI), returning language code, name, reliability flag, and probability score for 55 languages.

## Facts

- Endpoint: POST https://api.vextorium.com/v1/detect-language?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-19
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-language-detection-9a795ce5
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yI1vJZtvFgx1xSTOSYxn-

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-9a795ce5 -d '<json body>'
```

Example prompt: What language is this text written in? 'El tiempo libre es el mejor regalo que uno puede darse a sí mismo.' — I need the language name, ISO code, and how confident you are.

## When to prefer this

Choose this endpoint when you need fast, deterministic language detection without the latency or cost of an LLM-based approach. It is ideal for high-volume pipelines (e.g., routing, filtering, or pre-processing multilingual content) where statistical accuracy across 55 languages is sufficient and a probability/reliability score is valuable for downstream decisions. Prefer it over AI-based detection when cost per call and speed matter more than nuanced understanding of low-resource or dialect variants.

## Known failure modes

- Empty or very short text may produce unreliable detection with low probability score
- Ambiguous or mixed-language text may return 'reliable: false' with multiple alternatives
- Text with only numbers, symbols, or code may produce incorrect or low-confidence results
- Unsupported languages outside the 55-language model will be misidentified as a similar supported language
- Malformed request body missing required 'text' field will return an error

## 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: 'language' (ISO 639-1 code, e.g. 'es'), 'name' (human-readable language name, e.g. 'Spanish'), 'reliable' (boolean indicating whether detection confidence is high), 'probability' (float 0–1 indicating detection confidence), and 'alternatives' (array of other candidate languages with their scores).

## Request schema (JSON Schema)

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

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "name": "Spanish",
  "language": "es",
  "reliable": true,
  "probability": 1,
  "alternatives": []
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-language-detection-9a795ce5/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)