The paper introduces the Artificial Intelligence Forecasting System (AIFS), a data-driven weather forecasting model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, trained on ECMWF’s ERA5 re-analysis and operational numerical weather prediction (NWP) analyses. The model supports multiple levels of parallelism to enable training on high-resolution input data. AIFS is assessed by comparing its forecasts to NWP analyses and direct observational data, showing highly skilled forecasts for upper-air variables, surface weather parameters, and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF’s physics-based NWP model and is available to the public under ECMWF’s open data policy. The paper also discusses the model's architecture, training process, and limitations, highlighting its competitive performance and potential for probabilistic ensemble forecasting.The paper introduces the Artificial Intelligence Forecasting System (AIFS), a data-driven weather forecasting model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, trained on ECMWF’s ERA5 re-analysis and operational numerical weather prediction (NWP) analyses. The model supports multiple levels of parallelism to enable training on high-resolution input data. AIFS is assessed by comparing its forecasts to NWP analyses and direct observational data, showing highly skilled forecasts for upper-air variables, surface weather parameters, and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF’s physics-based NWP model and is available to the public under ECMWF’s open data policy. The paper also discusses the model's architecture, training process, and limitations, highlighting its competitive performance and potential for probabilistic ensemble forecasting.