# Anicca x402 Intent Router

> Anicca x402 Intent Router is a paid API for AI agents from x402-agents-production.up.railway.app, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-16).

Classifies free-text input against a caller-supplied list of intent labels, returning the best-matched intent with confidence score and extracted entities, paid per-call in USDC via x402.

## Facts

- Endpoint: POST https://x402-agents-production.up.railway.app/intent-router
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-16
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/anicca-x402-intent-router-ed7ab37c
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DfXc6AISza4Aev5kXiHMT

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 anicca-x402-intent-router-ed7ab37c -d '<json body>'
```

Example prompt: Route this message — 'I need to push my meeting to next Thursday' — against these intents: ['reschedule', 'cancel', 'book', 'confirm', 'query'] and tell me which one matches best and how confident you are, in English.

## When to prefer this

Choose this endpoint when you need lightweight, per-call intent classification with entity extraction that is billed micropayment-style in USDC via x402, making it ideal for AI agent pipelines that must pay only for what they use. It suits scenarios where you supply your own intent taxonomy (2–20 labels) and need structured routing decisions with confidence scores rather than a fixed, pre-trained classifier. Prefer it over heavyweight NLP APIs when you want zero infrastructure, multilingual support, and transparent per-call cost.

## Known failure modes

- Fewer than 2 intents provided — request rejected
- Text exceeds 2000 characters — validation error
- Unsupported language code provided — enum mismatch error
- Payment not settled via x402 — 402 Payment Required response
- Low confidence match when input is ambiguous across intents
- Context string exceeds 500 characters — validation error

## How this service works

Intent router for AI agents

## Output

Returns a JSON object containing the matched intent label and a unique intent ID, a confidence score (0–1), an optional secondary intent with its own confidence, a reasoning string explaining the classification, a list of extracted entities (type and value), and the detected language of the input.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "maxLength": 2000,
   "minLength": 1
  },
  "context": {
   "type": "string",
   "maxLength": 500
  },
  "intents": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "maxItems": 20,
   "minItems": 2
  },
  "language": {
   "enum": [
    "en",
    "ja",
    "es",
    "fr",
    "de",
    "zh",
    "ko"
   ],
   "type": "string",
   "default": "en"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "entities": [
   {
    "type": "date",
    "value": "Friday"
   }
  ],
  "intent_id": "int_a1b2c3",
  "reasoning": "The user asks to move an existing appointment.",
  "confidence": 0.97,
  "matched_intent": "reschedule",
  "secondary_intent": "book",
  "language_detected": "en",
  "secondary_confidence": 0.08
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/anicca-x402-intent-router-ed7ab37c/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-agents-production.up.railway.app](https://www.zero.xyz/host/x402-agents-production.up.railway.app/llms.txt)