Option valuation is one of the most important topics in financial economics. This study introduces a nonparametric version of the Esscher transform for risk neutral option pricing. Traditional parametric methods require the formulation of an explicit risk-neutral model and are operational only for a few probability density functions. In our proposal, we make only mild assumptions on the price kernel and there is no need for the formulation of the risk-neutral model for the returns. First, we simulate sample paths for the returns under the historical distribution P. Then, based on the Esscher transform, the sample is reweighted, giving rise to a risk-neutralized sample from which derivative prices can be obtained by a simple average of the pay-offs of the option to each path. We compare our proposal with some traditional pricing methods, applying four exercises under different situations, which seek to highlight the differences and similarities between the methods. Under the same conditions and in similar situations, the option pricing method proposed reproduces the results of pricing methods fully established in the literature, the Black and Scholes [3] model and the Duan [13] method. When the conditions are different, the results show that the method proposed indicates that there is more risk than the other methods can capture.