Metis 1 Preview

Metis is Parisi Labs' family of world models for physical systems, starting with energy. Metis 1 Preview is its first generation: probabilistic electricity price forecasts that read prices, load, generation and weather and forecast the full range of what power could cost at a location.

This card describes the model. Weights are not distributed; forecasts are served through Ask the Grid, the Forecast API and MCP.

What it produces


Target	Real-time electricity price at a settlement point
Output	A full probability distribution per interval, with p10, p50 and p90 bands and other published quantiles
Horizon	Adapted to the horizon a decision needs, rather than one fixed window
Coverage	US power markets, at nodes, zones and trading hubs
Issuance	Re-issued as conditions move. Every issuance is kept and scored as issued.

What it reads

Price is the target. Recent real-time prices, published day-ahead prices, load, generation and weather explain what the grid is doing, and every input is lined up to when it was actually available.

How to use it

Ask the Grid: the forecast sits beside observed real-time and cleared day-ahead prices on forecast pages, node pages and the map. Free with an account at major trading hubs and load zones; other locations come with a plan. See the ERCOT forecast.
Forecast API:
```
GET https://askthegrid.com/api/v1/grid/forecasts?iso=ERCOT&targetKind=node&targetId=HB_NORTH
```
Responses carry the issue time, quantile bands per interval, the settled price once it settles, and the build that produced each point. Open the playground.
MCP: give an AI agent the same forecasts as a tool. Connect over MCP.

Intended use

Comparing a location's outlook with cleared day-ahead prices
Sizing upper-tail spike risk and when the highest-price interval lands
Scoring forecast vintages against the prices that settled

Limits

Accuracy varies by market and lead time. Evaluate the horizon your decision depends on; scores by market and location are on the forecast accuracy board.
It forecasts prices. It is not a power-flow or transmission-network simulation.

About

Built by Parisi Labs. Read the thesis or the guide to reading a probabilistic price forecast. Contact: contact@parisi-labs.com.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Time Series Forecasting

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support