LLM chat completion

LLM chat completion. $0.01 USDC per call on Base, no API key. POST JSON { prompt } or { messages: [{ role, content }] }; optional model (OpenRouter slug) and max_tokens (default 800, max 2000). Falls back across up to 5 models so one outage does not fail the call. Returns { content, model, usage, latency_ms }.