# Carbon Cashmere Crypto Anomaly Detection

> Carbon Cashmere Crypto Anomaly Detection is a paid API for AI agents from api.carbon-cashmere.de, paid per call via x402, $0.08/call, status unknown (last checked 2026-09-15).

Detects anomalies in a cryptocurrency using z-score, STL decomposition, and IsolationForest methods, returning a composite anomaly score, severity classification, and top contributing features.

## Facts

- Endpoint: GET https://api.carbon-cashmere.de/v1/anomaly/:coin
- Price: $0.08/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-carbon-cashmere-de-966df771
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Xcb8QUf8qGmy6OqBrQJ9b

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 api-carbon-cashmere-de-966df771
```

Example prompt: Run a multi-method anomaly detection on BTC and tell me the composite anomaly score, severity level, and what the top driving features are.

## When to prefer this

Use this endpoint when you need a robust, ensemble-based anomaly signal for a specific cryptocurrency that combines statistical (z-score), time-series decomposition (STL), and machine learning (IsolationForest) methods into a single composite score. Prefer this over single-method anomaly checks when you want severity labeling and feature attribution alongside the score. Best for research, monitoring, or alerting workflows across the 34 supported coins.

## Known failure modes

- Unsupported coin ticker returns 404 or validation error — only 34 listed tickers are accepted
- Payment not attached or insufficient USDC triggers x402 payment required response
- Upstream data source unavailable causes 503 or partial results
- Invalid path parameter format returns 400 bad request

## How this service works

Multi-method anomaly detection combining z-score (returns/volume/funding), STL decomposition residuals, and IsolationForest. Returns composite anomaly score (0-1), severity classification (calm/elevated/extreme), and top contributing features. Informational research data — not investment advice.

## Output

Returns a JSON object containing: composite anomaly_score (0-1), severity classification string (calm/elevated/extreme), anomaly_flag boolean, per-method results breakdown, and an array of top_drivers (features most contributing to the anomaly), plus a _meta object and the coin symbol.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-carbon-cashmere-de-966df771/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.carbon-cashmere.de](https://www.zero.xyz/host/api.carbon-cashmere.de/llms.txt)