Activist investors and large holders of a US stock: SEC Schedule 13D (activist) and 13G (passive) filings of holders above 5% over days=1-1095, with holder names, type and percent of class. Use to find who owns 5% or more.

Fails to deliver of a US stock ($0.01): daily SEC data (up to 120 days), value, share of shares outstanding and the Reg SHO threshold pattern (10,000 shares and 0.5% for 5 days in a row) as a signal - THRESHOLD_LIKE, RECENT_THRESHOLD_LIKE, PERSISTENT_FAILS, OCCASIONAL_FAILS. Use before shorting or chasing a squeeze.

North American VIN check-digit validation (NHTSA standard, position 9) plus WMI manufacturer lookup for a small set of known codes.

Use to combine factor scores into one composite ($0.01), e.g. momentum, fundamentals and risk: send factors {name, score, weight}; get the 0-100 score with each factor's normalised weight and contribution. Weights need not sum to 1. Transparent and reproducible, no data fetched.

Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Use to average values you already have by importance ($0.01): send observations {value, weight}; get sum(value*weight)/sum(weight), the total weight and the count. Deterministic decimal math on your numbers, no market data fetched; any asset class or metric (scores, prices, returns, sentiment).

Use to rank a value against a dataset ($0.01), e.g. today's volume versus the last 90 days: send value and values; get its 0-100 percentile rank with counts below, equal and above. Methods LINEAR (default, interpolated), MIDRANK and AT_OR_BELOW. Deterministic, no data fetched.

Slugify text: strip accents, lowercase, replace non-alphanumerics with a separator.

Luhn (mod 10) checksum validation, as used by most payment card numbers.

Technical indicators of a crypto asset or stock: RSI(14), MACD(12,26,9), Bollinger(20,2) with %B, SMA20/50, ATR and VWAP on candles built from on-chain swaps (interval=1m, 5m, 15m, 1h), with bullish/bearish signals and a bias. Use for classic technical analysis.

Toxicity detection: classify text as toxic or not toxic (hate speech, harassment, threats, severe offensive language) with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /toxicity/sample.

Perp futures positioning and open interest for stocks and commodities (TSLA, NVDA, SPY, QQQ, AMZN, gold XAUUSD, oil WTIUSD, ...): long/short open interest per venue (GMX v2, gTrade), funding, 1h/24h change and a CROWDED_LONG/SHORT flag, next to spot DEX flow. Use to see whether a trade is crowded.

Spam detection: classify text as spam or not spam with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /spam-check/sample.

Sentiment analysis: classify text as positive, negative, or neutral with a confidence score and an alternate label. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable ("engine":"jev"|"fallback" in the response) - under 4.5s guaranteed. Try GET /sentiment/sample.

Language detection: identify which of 20 common languages (or "other") a text is written in, with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /language/sample.

Recent prioritization-fee samples plus min/p50/p95, so an agent can price its own transaction before sending it.

Compute an MD5, SHA-1, SHA-256 or SHA-512 hex digest of text.

Detect whether hex-encoded bytes are ASCII, UTF-8, or UTF-16 with a BOM, by decode-validity and BOM presence (not statistical language detection).

PII detection: flag whether text contains personally identifiable information (name plus contact details, email, phone, address, government ID, financial account) with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /pii-check/sample.

One call for the whole network picture: cluster health, current slot, epoch progress, SOL/USD price AND the top trending Solana pairs. Replaces 5 separate calls.