Over the last several years, highly accurate methods of sex selection before conception have been developed. Given that strong preferences for sex variety in offspring have been documented for the U.S., we ask what the demographic consequences of sex‐selection technology could be. Lacking variation across space and time in access to this technology, we estimate a dynamic programming model of fertility decisions with microdata on fertility histories. We leverage the quasi‐experimental variation inherent in the random determination of sex to identify the key structural parameter characterizing preferences for sex variety in offspring. We then simulate the introduction of this technology. While this technology can reduce fertility by allowing parents to efficiently reach their preferred sex mix, it could also increase it. This is because without this technology, many parents may opt not to have another baby given the uncertainty about its sex. Results suggest that these two effects operate simultaneously, but on net, sex‐selection technology ends up reducing the average family size among married women by less than 2% in the steady state, a much smaller decline than the one that would be predicted by alternative methods.