<strong class="journal-contentHeaderColor">Abstract.</strong> A multi-scale modeling ensemble chain has been assembled as a first step towards an Air Quality forecasting system for Latin America. Two global and three regional models were tested and compared over a shared domain (120W–28W, 60S–30N) to simulate January and July of 2015. Observations from local air quality monitoring networks in Colombia, Chile, Brazil, México, Ecuador and Peru were used for model evaluation. The models generally agreed with observations in large cities such as México City and São Paulo, whereas representing smaller urban areas, such as Bogotá and Santiago, was more challenging. For instance, in Santiago, during wintertime, the simulations showed large discrepancies with observations. No single model had the best performance among pollutants and sites available. Ozone and NO<sub>2</sub> were reproduced better than other pollutants across sites whereas SO<sub>2</sub> was the most difficult. The ensemble, created from the median value of the individual models, was evaluated as well. In some cases, the ensemble showed better results over the individual models and mitigated the extreme over- or underestimation of certain models, demonstrating the potential to establish an analysis and forecast system for Latin America. This study identified certain limitations in the models and global emissions inventories, which should be addressed with the involvement and experience of local researchers.
