In this study, we aimed to develop genomic estimated breeding values for heat tolerance in Australian dairy cattle. We combined test-day herd recording data with temperature and humidity measurements (in the form of temperature-humidity index or THI) from weather stations that were closest to the herds for test days between 2003 and 2013. High density SNP genotypes were available for the sires of the cows, and in some cases for the cows themselves. The reference population for genomic prediction was 2,300 Holstein and 575 Jersey genotyped sires with daughter trait deviations for response to heat stress for milk, fat and protein yield, and 2191 Holstein and 1191 Jersey cows with trait deviations for the same traits.  With this reference, and using GBLUP, the accuracy of genomic predictions for heat tolerance were 0.40 – 0.47 and 0.52 – 0.57 for 435 Holstein and 135 Jersey validation sires, respectively. When 2,191 Holstein cows and 1,190 Jersey cows were added in the reference populations, the accuracies were increased to 0.42-0.55 in Holsteins and 0.57-0.63 in Jerseys. With this level of prediction accuracy, genomic selection appears to be a useful tool to enable farmers to improve milk production in environments with higher heat load.