A new method has been introduced based on the idea of Marshall and Olkin. The proposed method can be applied to any distribution by inverting its quantile function as a function of Marshall Olkin method. We applied this method to the exponential distribution to obtain a two parameter Marshall Olkin within exponential quantile function. Several properties of the introduced distribution including mode, quantile function, moments, moment generating function, mean residual lifetime, entropy, order statistic, stress strength parameter and maximum likelihood estimation were highlighted. We illustrate the applicability of the introduced model to two different real data sets and it is observed that the proposed model leads to a better fit than all other competitive models.