EPT-2 Family
Jua's flagship state-of-the-art weather model was first released in April 2025. The EPT-2 family outperforms leading public AI weather models including Microsoft Aurora, DeepMind's GraphCast, ECMWF's AIFS, and our previous EPT-1.5 model.
EPT-2: Our deterministic model for precise weather forecasting
EPT-2 Early: Our early-dissemination model delivering forecasts ahead of the market
EPT-2e: Our ensemble model for probabilistic weather forecasting, especially for the long term
EPT-2 RR: Our rapid-refresh model for hourly global weather intelligence
EPT-2 HRRR: Our high-resolution rapid-refresh model
EPT-2 Reasoning: Our AI weather forecast model with active learning from live data
For more information on our EPT-2 family of models, take a look at our EPT-2 Technical Report.
EPT-2 Family Comparison
EPT-2
4 updates/day
20 days
EPT-2 Early
4 updates/day
20 days
EPT-2e
4 updates/day + 1 daily 60 day
60 days
EPT-2 RR
24 updates/day
2 days
EPT-2 HRRR
24 updates/day
2 days
EPT-2 Reasoning
4 updates/day
20 days
Live Forecast Data
Global coverage for EPT-2, EPT-2 Early, EPT-2e, and EPT-2 RR
European coverage for EPT-2 HRRR
Four daily runs (00, 06, 12, 18 UTC) for EPT-2, EPT-2 Early, EPT-2e
24 hourly runs for EPT-2 RR and EPT-2 HRRR
2-day prediction horizon (EPT-2 RR, EPT-2 HRRR)
20-day prediction horizon (EPT-2, EPT-2 Early, EPT-2e)
60-day prediction horizon for the EPT-2e forecast at 00 UTC
Real-time data access via Python SDK or REST API
Technical Specifications
Coordinates
Name
Description
Units
init_time
Initialization time of forecast at UTC
Absolute time (UTC)
prediction_timedelta
Lead time relative to initialization time
Timedelta
latitude
Latitudinal coordinate
Degrees true
longitude
Longitudinal coordinate
Degrees true
Spatial Extent
EPT-2
[90, -90)
[-180, 180)
2160x4320
0.081° (9 km)
EPT-2 Early
[90, -90)
[-180, 180)
1440x2880
0.125° (12 km)
EPT-2e
[90, -90)
[-180, 180)
720x1440
0.25° (25 km)
EPT-2 RR
[90, -90)
[-180, 180)
720x1440
0.25° (25 km)
EPT-2 HRRR
[36, 72]
[-15, 30]
720x900
0.05° (5.5 km)
EPT-2 Reasoning
[90, -90)
[-180, 180)
2160x4320
0.081° (9 km)
Available Weather Parameters
EPT-2 uses standardized variable naming conventions. For full details on the naming structure, see Weather Variable Naming.
2t
air_temperature_at_height_level_2m
Air temperature at 2m
Kelvin
2d
dew_point_temperature_at_height_level_2m
Dew point temperature at 2m
Kelvin
r
relative_humidity_at_height_level_2m
Relative humidity at 2m
%
10si
wind_speed_at_height_level_10m
Horizontal wind speed at 10m
m s⁻¹
10wdir
wind_direction_at_height_level_10m
Horizontal wind direction at 10m
Degrees true
100si
wind_speed_at_height_level_100m
Horizontal wind speed at 100m
m s⁻¹
100wdir
wind_direction_at_height_level_100m
Horizontal wind direction at 100m
Degrees true
msl
air_pressure_at_mean_sea_level
Mean Sea-level Pressure
Pa
lcc
low_type_cloud_area_fraction
Low Cloud Cover
%
mcc
medium_type_cloud_area_fraction
Medium Cloud Cove
%
hcc
high_type_cloud_area_fraction
High Cloud Cover
%
tp
precipitation_amount_sum_1h
Total Precipitation
mm m⁻²
ssrd
surface_downwelling_shortwave_flux_sum_1h
Surface solar downward irradiance
J m⁻²
fdir
surface_direct_downwelling_shortwave_flux_sum_1h
Direct solar radiation at the surface
J m⁻²
z_500
wind_direction_at_height_level_100m
Geopotential
m² s⁻²
Note: For information on the previous naming convention used in EPT-1.5, see Legacy Naming.
EPT-2 HRRR
EPT-2 HRRR produces a subset of the EPT-2 variables.
2t
air_temperature_at_height_level_2m
Air temperature at 2m
Kelvin
10si
wind_speed_at_height_level_10m
Horizontal wind speed at 10m
m s⁻¹
10wdir
wind_direction_at_height_level_10m
Horizontal wind direction at 10m
Degrees true
100si
wind_speed_at_height_level_100m
Horizontal wind speed at 100m
m s⁻¹
100wdir
wind_direction_at_height_level_100m
Horizontal wind direction at 100m
Degrees true
msl
air_pressure_at_mean_sea_level
Mean Sea-level Pressure
Pa
tcc
cloud_area_fraction_at_entire_atmosphere
Total Cloud Cover
%
ssrd
surface_downwelling_shortwave_flux_sum_1h
Surface solar downward irradiance
J m⁻²
Additional Variables on Request
tcwv
atmosphere_mass_content_of_water_vapor
Total column vertically-integrated water vapour
kg m⁻²
t
air_temperature_at_pressure_level
Temperature at a specified pressure level
K
u
eastward_wind_at_pressure_level
U component of wind
m s⁻¹
v
northward_wind_at_pressure_level
V component of wind
m s⁻¹
q
specific_humidity_at_pressure_level
The mass of water vapour per kilogram of moist air at a pressure level
kg
z
geopotential_at_pressure_level
The gravitational potential energy of a unit mass
m² s⁻²
Pressure levels: 5'000, 10'000, 15'000, 20'000, 25'000, 30'000, 40'000, 50'000, 60'000, 70'000, 85'000, 92'500, 100'000
Hindcast Data
Data Access: Hindcasts are available via our Python SDK and API. For large requests, please contact [email protected].
Model
Temporal Extent
Forecast Horizon and Resolution
EPT-2
2023-01-01 - today
at 00, 06, 12, 18 UTC
480h
- From 1h to 240h: hourly
- From 240h to 480h: six-hourly
EPT-2e
2025-08-16 - today
at 00, 06, 12, 18 UTC
00 UTC: 1440h; 06, 12, 18 UTC: 480h
- From 1h to 240h: hourly
- From 240h to 480h/1440h: six-hourly
EPT-2 RR
2024-01-01 - today
at 00-23 UTC (every hour)
48h, hourly
EPT-2 HRRR
2025-10-06 - today
at 00-23 UTC (every hour)
48h, hourly
EPT-2 Early
2025-09-01 - today
at 00, 06, 12, 18 UTC
480h
- From 1h to 240h: hourly
- From 240h to 480h: six-hourly
EPT-2 Reasoning
2025-08-16 - today
at 00, 06, 12, 18 UTC
480h
- From 1h to 240h: hourly
- From 240h to 480h: six-hourly
Extended Hindcast Data (Special Request Only)
Special Request Required: The following extended hindcast data is available but requires special access permissions and is not accessible through standard API/SDK access. Please contact [email protected] to request access.
Model
Extended Temporal Coverage
Forecast Horizon and Resolution
EPT-2 Early
2024-03-01 - 2024-03-13, 2024-06-05 - 2024-12-31
at 00, 06, 12, 18 UTC
480h
- From 1h to 240h: hourly
- From 240h to 480h: six-hourly
Performance Benchmarks
EPT-2 consistently outperforms other leading weather models, including:
Microsoft Aurora
DeepMind's GraphCast
ECMWF's AIFS
Our previous EPT-1.5 model
For more details on EPT-2 performance benchmarks, check out our benchmarking analysis.
Dissemination Times
For detailed dissemination times of the EPT-2 family please refer to the Dissemination Times page.
Last updated