# Carbon & Cashmere Signal Accuracy API – ETH

> Carbon & Cashmere Signal Accuracy API – ETH is a paid API for AI agents from api.carbon-cashmere.de, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-14).

Returns ML model signal accuracy statistics, calibration data, and prediction performance metrics for Ethereum (ETH) over a 180-day lookback window.

## Facts

- Endpoint: GET https://api.carbon-cashmere.de/v1/signal-accuracy/ETH
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/carbon-cashmere-signal-accuracy-api-eth-f5c5ee08
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Nw3Vh6xTMO4YB69yWVRw0

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 carbon-cashmere-signal-accuracy-api-eth-f5c5ee08
```

Example prompt: Pull the Carbon & Cashmere signal accuracy stats for ETH — I want to see how well the ML model has been predicting price direction, including the calibration gap and edge over coinflip over the past 180 days.

## When to prefer this

Use this endpoint when you need quantified, backtested accuracy and calibration data for the ETH ML signal model specifically — not raw price data or live signals. Ideal for evaluating whether the signal is trustworthy before acting on it, or for monitoring model drift over time. Prefer this over general market data endpoints when the question is 'how good is this signal?' rather than 'what is the signal?'

## Known failure modes

- Coin symbol not supported — endpoint is hardcoded to ETH; other tickers may 404
- Insufficient sample size for certain time windows — labeled in response as inadequate
- Payment not processed — x402 payment required at $0.02 USDC per call; unpaid requests will be rejected
- Stale data — if model has not run recently, accuracy stats may reflect older period
- Malformed response if upstream ML pipeline has an error

## How this service works

Professional crypto market intelligence. Real-time prices, signals, and market scoring.

## Output

A JSON object containing: coin identifier, model-level accuracy stats (correct predictions, total predictions, accuracy rate, avg confidence, edge vs coinflip in basis points), calibration classification (e.g. overconfident) with gap in bps, lookback period in days, best performing model summary, per-time-window accuracy breakdown, and confidence bucket accuracy breakdown.

## Request schema (JSON Schema)

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

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "coin": "BTC",
  "_meta": {
   "disclaimer": "Informational research data only — not investment advice."
  },
  "models": [
   {
    "model": "v3_tsfresh",
    "correct": 469,
    "accuracy": 0.6228,
    "avg_confidence": 0.7274,
    "total_predictions": 753,
    "edge_vs_coinflip_bps": 1228.4
   }
  ],
  "calibration": {
   "gap_bps": 1046,
   "classification": "overconfident",
   "avg_confidence_primary_model": 0.7274,
   "actual_accuracy_primary_model": 0.6228
  },
  "lookback_days": 180,
  "best_performing_model": {
   "name": "v3_tsfresh",
   "accuracy": 0.6228,
   "sample_size": 753
  },
  "time_windows_v3_tsfresh": [
   {
    "accuracy": 0.6429,
    "window_days": 7,
    "total_predictions": 42,
    "sample_size_adequacy": "adequate"
   }
  ],
  "confidence_buckets_v3_tsfresh": [
   {
    "total": 180,
    "accuracy": 0.65,
    "confidence_bucket": "high"
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/carbon-cashmere-signal-accuracy-api-eth-f5c5ee08/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)