Why regime, not point forecast.

Wholesale electricity already has plenty of point-price vendors. What's missing — what procurement and trading desks actually hit a wall on — is a stable, calibrated signal about whether the distribution around today's price just shifted. Amanoki publishes that signal. This page is the one-screen answer to "why this, in this form".

Point forecasts self-destruct

A perfect short-term price prediction, priced and sold, gets arbitraged away the moment enough customers act on it. That's the self-referential trap every price-forecast vendor eventually hits: success narrows alpha, alpha narrowing churns customers, churn pushes the vendor to more aggressive claims, claims erode trust. A regime label and a spike probability don't collapse that way — both are summary statistics of market behaviour, not directional trading signals.

Regimes are commercial, not statistical

The four states (low / normal / high / scarcity) map to procurement and trading actions the way price levels don't. A scarcity bar on a cold winter morning moves a retailer's monthly procurement cost more than ten forecasted prices do. The FSM stabilises the scarcity boundary (absolute ¥/kWh threshold) and the volatility boundary (hysteresis over a z-score ladder) in a way that smooths single-bar noise without lagging too far behind real transitions.

Calibrated probability beats direction

regime-forecast returns P(regime_{t+H}) — a full distribution, not a top-pick prediction. The same response carries the held-out Brier score and the unconditional baseline Brier so callers can judge calibration for themselves. That's the posture that survives adoption: we publish what we know and how well we know it; you decide what to do with it.

Weather is the exogenous lever

Current weather (temperature, wind, irradiance, cloud cover, humidity) drives the regime model alongside the FSM's own lagged state. Weather doesn't react to market participants, so conditioning on it doesn't self-destruct. As more weather signals (Open-Meteo today, higher-resolution NWP later) land, the same endpoint shape absorbs them — callers don't rewrite against a v1 to v1.5 model upgrade.

What you're paying for when tiers open

Rate limit, archive depth, and early access to new forecast families — not a different set of numbers on the same response. The free tier and paid tiers return the same content for any request both are allowed to make. If a paid-tier customer publishes their Brier score, a free-tier caller can verify it against the same endpoint.

What you're not getting