# Carbon Cashmere Per-Coin ML Feature Vector

> Carbon Cashmere Per-Coin ML Feature Vector is a paid API for AI agents from api.carbon-cashmere.de, paid per call via x402, $0.01/call, status down (last checked 2026-09-15).

Returns a 46-field ML feature vector for a specified cryptocurrency, including price returns, volatility, volume, RSI/MACD, Fear & Greed index, funding rates, open interest, options data, orderbook microstructure, and on-chain signals — with a 6-hour delay.

## Facts

- Endpoint: GET https://api.carbon-cashmere.de/v1/features/:coin
- Price: $0.01/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-carbon-cashmere-de-5b02322e
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_9aH7EZD634Q648nxEmo0f

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-5b02322e
```

Example prompt: Pull the full 46-field ML feature vector for BTC from Carbon Cashmere — I need all the TA indicators, funding rate, open interest, orderbook microstructure, and on-chain whale signals so I can feed it into my prediction model.

## When to prefer this

Prefer this endpoint when you need a comprehensive, pre-computed ML feature vector for a single cryptocurrency that spans technical analysis, market microstructure, and on-chain signals in one call. Ideal for feature engineering pipelines, backtesting, and training supervised ML models where 6-hour latency is acceptable. Use over building your own feature pipeline when you want a standardized 46-field representation covering RSI/MACD, funding, OI, whale activity, and mempool in a single request.

## Known failure modes

- Unsupported coin ticker returns 404 or empty result
- 6-hour data delay means real-time signals are not available
- Payment failure via x402 protocol results in 402 response
- Coin with insufficient liquidity may have missing or null fields for options/orderbook features
- Rate limiting or quota exceeded returns 429 error

## How this service works

Per-coin ML feature vector (46 fields, 6h-delayed) — price returns, volatility, volume, RSI/MACD, Fear & Greed, funding, OI, options, orderbook, on-chain (whale, mempool). Standard TA + market microstructure. AI agent API for feature engineering and research.

## Output

A JSON object containing 46 ML-ready feature fields for the requested coin: price return metrics, realized and implied volatility, volume statistics, RSI and MACD values, Fear & Greed index score, perpetual funding rates, open interest, options market data, L2 orderbook bid/ask imbalance and spread, on-chain whale flow, and mempool signals. Data is sourced from standard technical analysis plus market microstructure and is delayed by 6 hours.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-carbon-cashmere-de-5b02322e/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)