Call when screening several Base tokens at once, e.g. new launches: up to 10 tokens per call, same checks as /api/token/check (sell simulation, taxes, owner powers, liquidity, holders). All-or-nothing: a failed batch is not charged.

Call before buying or swapping into any Base token. Simulates a real buy and sell in its deepest pool (honeypot, buy/sell tax, round-trip loss), reads owner powers (mint, pause, blacklist, tax, proxy), liquidity, age and holder concentration. Returns SAFE / CAUTION / DANGER / SCAM with every risk explained. Failed checks are not charged.

Call before paying an unfamiliar x402 endpoint. Sends an unpaid request and validates its 402, compares price and payTo with its Bazaar listing (catches hijacked payTo), and scores 30-day demand for fake-traffic patterns. Returns TRUSTED / OK / SUSPECT / AVOID.

Call when you need the readable content of a public web page: returns clean markdown (title, headings, lists, links; scripts and navigation removed), up to 100k characters. Pages that fail (404, blocked, timeout) are not charged.

Call when you need an LLM completion and have no API key: OpenAI-compatible chat completions (DeepSeek chat model), pay per call. Up to 16000 characters in, 512 tokens out, no streaming. Invalid requests are not charged.