# Market Intelligence API – Anomaly Score

> Market Intelligence API – Anomaly Score is a paid API for AI agents from api.marketintelligenceapi.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-28).

Computes a statistical anomaly score (0–100) for a single value relative to a reference set, returning z-score, severity, and direction using fixed statistical thresholds.

## Facts

- Endpoint: POST https://api.marketintelligenceapi.com/api/v1/analytics/anomaly-score?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/market-intelligence-api-anomaly-score-56536e6f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_1V1ndjawRkV5BpI6axVs0

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 market-intelligence-api-anomaly-score-56536e6f -d '<json body>'
```

Example prompt: Score today's BTC daily return of 8.2% against the last 30 days of returns — [3.1, -1.2, 0.8, 2.4, -0.5, 1.1, -2.3, 4.0, 0.3, -0.9, 1.7, -1.5, 2.8, -3.2, 0.6, 1.9, -0.7, 3.5, -1.8, 0.2, 1.3, -0.4, 2.1, -2.0, 0.9, 1.6, -1.1, 3.8, -0.6, 2.5] — using sample standard deviation and tell me the anomaly score, z-score, severity, and whether it's above or below the norm.

## When to prefer this

Choose this endpoint when you need a fast, deterministic, purely statistical outlier score with no AI model latency or hallucination risk. It is ideal for automated pipelines that need to classify a single observation against a known reference distribution and get a structured severity label — especially when reproducibility and fixed thresholds matter. Prefer alternatives when you need probabilistic forecasting, time-series trend detection, or anomaly detection that accounts for seasonality and autocorrelation.

## Known failure modes

- Too few reference values (fewer than 2) — schema requires minItems: 2
- All reference values identical (zero standard deviation) — z-score is undefined, likely returns error
- Non-numeric or malformed value inputs causing schema validation failure
- Exceeding 10,000 reference values — rejected by maxItems constraint
- Missing required 'value' or 'values' fields — returns 400-level error

## How this service works

Use to flag outliers in any series ($0.01): send value and reference values; get a 0-100 anomaly score, the z-score, severity (NORMAL, LOW, MEDIUM, HIGH, EXTREME) and direction (ABOVE/BELOW). Fixed statistical thresholds, no AI and no data fetched; a score, not a probability.

## Output

Returns a JSON object containing: a numeric anomaly score from 0 to 100 (higher = more anomalous), the z-score of the submitted value relative to the reference set, a severity label (NORMAL, LOW, MEDIUM, HIGH, or EXTREME), and a direction indicator (ABOVE or BELOW the mean). No probabilities, no AI inference — purely statistical output based on fixed thresholds.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "value": {
   "type": "number",
   "description": "The observation to score"
  },
  "method": {
   "enum": [
    "SAMPLE",
    "POPULATION"
   ],
   "type": "string",
   "default": "SAMPLE",
   "description": "Standard deviation: SAMPLE divides by n-1, POPULATION by n"
  },
  "values": {
   "type": "array",
   "items": {
    "type": "number",
    "description": "Reference value"
   },
   "maxItems": 10000,
   "minItems": 2
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/market-intelligence-api-anomaly-score-56536e6f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.marketintelligenceapi.com](https://www.zero.xyz/host/api.marketintelligenceapi.com/llms.txt)