An experimental design has been used to optimize the extraction of antioxidants from the microalga Spirulina platensis using accelerated solvent extraction (ASE) with four different solvents (hexane, petroleum ether, ethanol and water). The optimization of the main variables involved in the ASE process (extraction temperature and time) has been done by means of a full factorial (three levels) design using, as responses, the extraction yield and the antioxidant activity of the extracts (determined as EC50, i.e., efficient concentration, using an in vitro assay based on a free radical method). The parameters of the model, for each response variable, were estimated by multiple linear regression (MLR). The statistical analysis of the results provided mathematical models that allowed prediction of the behaviour of the different responses selected, as a function of the main variables involved in the process. It was observed that the optimum conditions that maximize yield and minimize EC50 depend on the polarity of the solvent used to perform the extractions. Extraction temperature had an enormous influence in both responses while the effect of extraction time was almost negligible.Ethanol was finally selected as the extracting solvent for its GRAS (Generally Recognized as Safe) status and because it provides higher yields with medium antioxidant activities. The results presented in this work show the possibility of using a fast and easy process to recover natural antioxidants from natural sources such as microalgae.