The mixtools package for R provides a comprehensive set of functions for analyzing various finite mixture models. These functions include both traditional methods, such as EM algorithms for univariate and multivariate normal mixtures, and newer methods that reflect recent research in finite mixture models. The package supports a wide range of mixture-of-regression contexts, multinomial mixtures arising from discretizing continuous multivariate data, nonparametric situations where the multivariate component densities are completely unspecified, and semiparametric situations like univariate location mixtures of symmetric but otherwise unspecified densities. Many of the algorithms in mixtools are based on EM algorithms or are inspired by EM-like ideas, making it a valuable tool for unsupervised clustering and model-based clustering. The package is available from the Comprehensive R Archive Network (CRAN) and includes functions for fitting and visualizing mixture models, as well as for performing statistical inference. The article provides an overview of EM algorithms for finite mixture models and discusses various categories of functions in the mixtools package, including cutpoint methods, nonparametric and semiparametric methods, and mixtures of regressions.The mixtools package for R provides a comprehensive set of functions for analyzing various finite mixture models. These functions include both traditional methods, such as EM algorithms for univariate and multivariate normal mixtures, and newer methods that reflect recent research in finite mixture models. The package supports a wide range of mixture-of-regression contexts, multinomial mixtures arising from discretizing continuous multivariate data, nonparametric situations where the multivariate component densities are completely unspecified, and semiparametric situations like univariate location mixtures of symmetric but otherwise unspecified densities. Many of the algorithms in mixtools are based on EM algorithms or are inspired by EM-like ideas, making it a valuable tool for unsupervised clustering and model-based clustering. The package is available from the Comprehensive R Archive Network (CRAN) and includes functions for fitting and visualizing mixture models, as well as for performing statistical inference. The article provides an overview of EM algorithms for finite mixture models and discusses various categories of functions in the mixtools package, including cutpoint methods, nonparametric and semiparametric methods, and mixtures of regressions.