In this study a commercially available electronic tongue (αAstree, Alpha M.O.S.) was employed as a technique for gluten free and regular flour samples classification. Additionally, rapid determination of gluten content and other physicochemical parameters including protein content, acidity, reducing sugar content and total reducing sugar content was performed. The classification performance of the sensor array was assessed by multivariate exploratory techniques. The physicochemical characterization of gluten free and regular flours, including gluten content prediction, was obtained by artificial neural networks (ANN) modelling. The reference values of gluten content in flour samples were determined by the ELISA method, while reference values of protein content, acidity, reducing sugar content and total reducing sugar content were determined by standard analytical methods. The application of the electronic tongue, combined with ANN, in the differentiation of gluten free and regular flour samples resulted in 95.2% and 100% correct classifications, respectively. The developed ANN models for the prediction of gluten content in flour samples as well as protein content, acidity, reducing sugar content and total reducing sugar content, showed high potential of the electronic tongue as a simple and rapid technique for the prediction of gluten content and other physicochemical parameters of gluten free and regular flour samples. The results of this work implicate that the electronic tongue can be employed in the evaluation of gluten content and characterization of different flours, without time-consuming sample preparation, chemicals involved and without additional time or costs, except the initial measurements required for ANN model development.