As fire seasons in Brazil lengthen and intensify, the need to enhance fire simulations and comprehend fire drivers becomes crucial. Yet determining what drivers burning in different Brazilian biomes is a major challenge, with the highly uncertain relationship between drivers and fire. Finding ways to acknowledge and quantify that uncertainty is critical in ascertaining the causes of Brazil’s changing fire regimes. We propose FLAME (Fire Landscape Analysis using Maximum Entropy), a new fire model that integrates Bayesian inference with the Maximum Entropy (MaxEnt) concept, enabling probabilistic reasoning and uncertainty quantification. FLAME utilizes bioclimatic, land cover and human driving variables to model fires. We apply FLAME to Brazilian biomes, evaluating its performance against observed data for three categories of fires: all fires (ALL), fires reaching natural vegetation (NAT), and fires in non-natural vegetation (NON). We assessed burned area responses to variable groups. The model showed adequate performance for all biomes and fire categories. Maximum temperature and precipitation together are important factors influencing burned area in all biomes. The number of roads and amount of forest boundaries (edge densities), and forest, pasture and soil carbon showed higher uncertainties among the responses. The potential response of these variables displayed similar spatial likelihood of the observations given the model, between the ALL, NAT and NON categories. Overall, the uncertainties were larger for the NON-category, particularly for Pampas and Pantanal. Customizing variable selection and fire categories based on biome characteristics could contribute to a more biome-focused and contextually relevant analysis. Moreover, prioritizing regional-scale analysis is essential for decision-makers and fire management strategies. FLAME is easily adaptable to be used in various locations and periods, serving as a valuable tool for more informed and effective fire prevention measures.