Corollary

Research

  • Papers

Library

  • Catalog

Account

  • Jobs
  • Billing
SettingsResearch demo · not for clinical or commercial use
Corollary
  1. Catalog
  2. Multi-Modal Foundation
  3. AIFS Single 1.0

Multi-Modal Foundation · ecmwf

AIFS Single 1.0

First 1.0 release of the deterministic AIFS — graph-based global weather forecasting model from ECMWF on the Anemoi framework.

Verify the licence before commercial useThe See model card licence carries terms worth reading before you depend on it.See model card
Availability
On demand
Typical latency
12s
Credits per run
~28
Compute tier
S · Micro

< 1s

Runs on On-demand GPU

Runs on our servers with on-demand compute. A first run needs time to load the model; active capacity can be reused and scales down when idle.

Run this model

AIFS Single 1.0

Forecast ahead

Measured from the most recent analysis ECMWF has published.

Field

up to 70 credits · ~12s typical

About this model

First 1.0 release of the deterministic AIFS — graph-based global weather forecasting model from ECMWF on the Anemoi framework. Served through the generic Modal runner, which pulls ecmwf/aifs-single-1.0 from the Hugging Face Hub and runs it as a graph-ml pipeline. Inputs and outputs were derived from the repository's declared pipeline tag rather than written by hand — check the model card before relying on a result.

Standardized I/O contract

Every model in the Hub speaks the same contract, which is what lets the Router and the agent call any of them without special-casing.

Inputs

  • lead_timeselect · required

    Forecast ahead

  • variableselect · required

    Field

Outputs

  • mapimage

    The chosen field over the globe at the forecast time.

  • summarytable

    Analysis time, valid time and the field's range.

Specification

Hardware
CPU only
GPU memory
16 GB
Version
hub
Licence
See model card
Backend
On demandOn-demand GPU
MCP server
mcp-sandbox-server

Tasks

forecasting

Source

  • Model card
  • Repository
earth-scienceclimatephysicsgraph-ml