The use of blasting cost (BC) prediction to achieve optimal fragmentation is necessary in order to control the adverse consequences of blasting such as fly rock, ground vibration, and air blast in open-pit mines. In this research work, BC is predicted through collecting 146 blasting data from six limestone mines in Iran using the artificial neural networks (ANNs), gene expression programming (GEP), linear multivariate regression (LMR), and non-linear multivariate regression (NLMR) models. In all models, the ANFO value, number of detonators, Emolite value, hole number, hole length, hole diameter, burden, spacing, stemming, sub-drilling, specific gravity of rock, hardness, and uniaxial compressive strength are used as the input parameters. The ANN model results in the test stage indicating a higher correlation coefficient (0.954) and a lower root mean square error (973) compared to the other models. In addition, it has a better conformity with the real blasting costs in comparison with the other models. Although the ANNs method is regarded as one of the intelligent and powerful techniques in parameter prediction, its most important fault is its inability to provide mathematical equations for engineering operations. In contrast, the GEP model exhibits a reliable output by presenting a mathematical equation for BC prediction with a correlation coefficient of 0.933 and a root mean square error of 1088. Based on the sensitivity analysis, the spacing and ANFO values have the maximum and minimum effects on the BC function, respectively. The number of detonators, Emolite value, hole number, specific gravity, hardness, and rock uniaxial compressive strength have a positive correlation with BC, while the ANFO value, hole length, hole diameter, burden, spacing, stemming, and sub-drilling have a negative correlation with BC.