Zero-shot text classification into caller-supplied labels, via Claude Haiku.

Phishing/scam risk heuristics for a domain name — TLD, lookalike/typosquat patterns, structural flags, plus a Haiku judgment call.

Fetch a URL and extract structured data via Claude Haiku, optionally guided by a JSON schema hint.

Fact-check verdict (true/false/uncertain) with confidence and reasoning for a factual claim, via Claude Haiku.

Grid-trading parameter recommendation (grid count, spacing, price band, per-grid allocation) for a crypto pair and capital amount, derived from live 24h market structure using a production grid engine's bounds.

Fetch a URL and return clean markdown, stripped of nav/ads/scripts.

Current price, 24h and 7d percent change, and a bullish/bearish/neutral signal for a crypto asset (SOL, BTC, ETH, XRP, DOGE, LTC, ADA, XLM). For agents needing a fast price-and-momentum check before a trade decision. Optional ?candles=N (up to 30, $0.05) adds N closed daily OHLC candles.

Crypto market regime classification (choppy / uptrend / downtrend / high-volatility) for SOL, BTC, ETH, XRP, DOGE, LTC, ADA, or XLM, plus a grid-trading suitability verdict. Computed live from 1h klines, a 30-day volatility baseline, and EMA trend detection — the same classifier that steered our production grid bot before we retired it 2026-08-16. For agents deciding whether a pair is grid-tradeable right now.

Volatility / drawdown risk regime for a crypto asset, extending the same classifier behind /regime.

Sentiment score (-1 bearish to +1 bullish) and label for arbitrary text, or for a crypto asset based on its recent price action, via Claude Haiku. For agents gauging market mood or scoring news, social posts, or free text.

Tight Claude Haiku summary of a URL or raw text.

Historical telemetry from our retired grid-trading bot - allocation, reconciled P&L, signal votes, and the human-approval trail for every trade. The bot stopped trading 2026-08-16; this endpoint serves its frozen record.

Risk flags for an EVM token/contract — liquidity, pair age, and volume pulled from DexScreener, scored into a 0-100 risk score and verdict.