In this study, a genetic algorithm has been employed to determine optimum cutting parameters in the turning of T16Al4V alloy under conventional and high pressure cooling conditions. Three machining performance measures, i.e. surface roughness, material removal rate and cutting power, are considered as optimization criteria. First, with multi-regression analysis of experimental responses, empirical equations are defined and, by using these equations, objective functions are constructed for each pressure level, based on a hybrid model. Objective functions are maximized by means of a genetic algorithm and optimum machining parameters are determined. Moreover, tool wear tests are carried out at a cutting condition that is close to the optimum machining parameters. Optimization results show that optimum cutting parameters and their responses, particularly in P = 6 and 150 bar cooling conditions, are quite similar, but tool life is significantly different. Maximum tool life is achieved in the highest pressure level (P = 300 bar).