Third Party Models

The Jua platform provides access to several third-party weather models alongside our proprietary EPT models. These models can be accessed through both the platform interface and API.

Available Models

ECMWF Models

• ECMWF IFS Operational - ECMWF IFS HRES model, often referred as ops. See ECMWF IFS for details.

• ECMWF IFS Ensemble - Multiple ECMWF IFS Ensemble runs, often referred to as ENS. See ECMWF IFS Ensemble for details.

• ECMWF AIFS - EC's AI-based forecasting model (learn more)

NOAA Models

• GFS - Global Forecast System from NOAA. See GFS NOAA for details.

• GFS Ensemble Mean - Average of multiple GFS ensemble runs

AI Models

• Microsoft Aurora - Microsoft's AI-based global weather model. See Microsoft Aurora for details.

• GFS GraphCast - Google DeepMind's ML-based weather prediction model, initialised by GFS. See GFS GraphCast for details.

DWD Models

• ICON Global - Global model from DWD (Deutscher Wetterdienst). See DWD ICON Global for details.

• ICON-EU - Higher-resolution regional European model from DWD (Deutscher Wetterdienst). See DWD ICON-EU for details.

Regional Models

• AROME France HD - High-definition regional model from Météo-France

Open Meteo Models

Additional models are available through Open Meteo, including ECMWF AIFS/IFS variants, GFS/NCEP models, and regional European models (ICON-D2, KNMI HARMONIE-AROME, AROME France HD, UKMO). These models have some restrictions: point queries, no streaming, latest forecast, and nearest interpolation. See Open Meteo Models for the full list.

Hindcasts

The following hindcast datasets are available:

• ECMWF AIFS - Historical forecast data available for performance analysis and evaluation. See ECMWF AIFS for details.

• ECMWF IFS Operational - Historical forecast data available. See ECMWF IFS for details.

• GFS NOAA - Historical forecast data available. See GFS NOAA for details.

• Microsoft Aurora - Hindcast data available. See Microsoft Aurora for details.

API Access

To access these third-party weather models, specify the model name in your API requests:

# ECMWF Operational
GET /v1/forecasting/ecmwf-operational/forecasts/latest/47.37,8.54

# ECMWF Ensemble Mean
GET /v1/forecasting/ecmwf-ensemble-mean/forecasts/latest/47.37,8.54

# ECMWF AIFS
GET /v1/forecasting/ecmwf-aifs/forecasts/latest/47.37,8.54

# GFS
GET /v1/forecasting/gfs/forecasts/latest/47.37,8.54

# GFS Ensemble Mean
GET /v1/forecasting/gfs-ensemble-mean/forecasts/latest/47.37,8.54

# ICON Global
GET /v1/forecasting/icon-global/forecasts/latest/47.37,8.54

# ICON-EU (European regional model)
GET /v1/forecasting/icon-eu/forecasts/latest/47.37,8.54

# AROME France HD (regional model)
GET /v1/forecasting/arome-france-hd/forecasts/latest/48.85,2.35

Open Meteo models are accessed through the Query Engine API (POST /v1/forecast/data) rather than the legacy GET endpoints above. See Open Meteo Models for details and examples.

For historical forecasts, you can use the init_time parameter:

GET /v1/forecasting/ecmwf-operational/forecasts/20240310T000000Z/47.37,8.54

Format: YYYYMMDDTHHMMSSZ (ISO 8601 format with Z indicating UTC time)

For complete API documentation, please refer to our API Reference.