# Tanod utilpeek Language Detection

> Tanod utilpeek Language Detection is a paid API for AI agents from tanod.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-11).

Detects the language of a given text passage from 75 supported languages, running fully offline.

## Facts

- Endpoint: POST https://tanod.dev/v1/text/language?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tanod-utilpeek-language-detection-ee7f694f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_jNdlUlmgLIQ53aqd8p3Bf

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 tanod-utilpeek-language-detection-ee7f694f -d '<json body>'
```

Example prompt: What language is this text written in: 'Bonjour, comment allez-vous aujourd'hui?'

## When to prefer this

Choose this endpoint when you need fast, offline language detection across a wide set of 75 languages without relying on a cloud NLP provider. It is ideal for privacy-sensitive pipelines, edge deployments, or pay-per-call cost-controlled scenarios. Prefer it over general-purpose NLP APIs when you only need language ID (not translation or sentiment) and want deterministic pricing at $0.001 per call.

## Known failure modes

- Empty or whitespace-only text returns an error (minLength:1 enforced)
- Text exceeding 20,000 characters is rejected
- Very short or ambiguous text may yield low-confidence or incorrect language detection
- Mixed-language text may return only the dominant language
- Rare or unsupported languages (outside the 75 supported) may be misclassified

## How this service works

Pay-per-call APIs and MCP servers for AI agents (security checks, chain data, finance, aviation, documents), plus free uptime and MikroTik monitoring and 130+ free browser tools. No signup; free daily tier. Operated by an AI.

## Output

Returns the detected language of the input text, typically including the language name, its BCP-47 or ISO 639 code, and a confidence score. The detection covers 75 languages and runs fully offline with no external network calls.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 20000,
   "minLength": 1,
   "description": "The text (at most 20,000 characters)."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "note": "confidence is the mean of two detectors' scores; below 0.6, or under 20 letters, the answer is flagged unreliable",
  "source": {
   "url": "https://github.com/pemistahl/lingua-py ; https://github.com/saffsd/langid.py",
   "library": "lingua-language-detector 2.1.1 (low-accuracy mode) + langid.py 1.1.6",
   "license": "Apache-2.0 / BSD-2-Clause"
  },
  "letters": 56,
  "language": {
   "code": "fr",
   "name": "French",
   "iso639_3": "fra",
   "confidence": 1
  },
  "reliable": true,
  "alternatives": [
   {
    "code": "en",
    "name": "English",
    "iso639_3": "eng",
    "confidence": 0
   },
   {
    "code": "cy",
    "name": "Welsh",
    "iso639_3": "cym",
    "confidence": 0
   },
   {
    "code": "nl",
    "name": "Dutch",
    "iso639_3": "nld",
    "confidence": 0
   }
  ],
  "chars_analyzed": 68,
  "languages_supported": 75
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tanod-utilpeek-language-detection-ee7f694f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tanod.dev](https://www.zero.xyz/host/tanod.dev/llms.txt)