The formation of unwanted oil emulsions during the production, transportation, and processing of crude oil is a major challenging issue. This causes serious technical problems and, subsequently, huge financial losses, which indicate the importance of their separation. The present work investigated the influence of an efficient oil-soluble demulsifier and temperature on the Demulsification Efficiency (DE) of water-in-crude oil emulsions through the bottle test method. The Central Composite Design (CCD) based on Response Surface Mythology (RSM) was applied to design the experiments and optimize the demulsification process. Based on the experimental results, a reduced quadratic model was developed using CCD. In addition, the analysis of variance (ANOVA) was used to evaluate the significance of the developed model and operational parameters. It was found that the P-value of the DE model was less than 0.0001, which confirms the considerable significance of the developed model. Moreover, R2, adj-R2, and pred-R2 were 98.89, 98.15, and 94.34%, which indicates the high accuracy of the proposed model. The result showed that the effect of the demulsifier at low temperatures (25-50 oC) was significantly weak on the separation efficiency of the studied emulsions. In this case, the maximum water removal from the oil emulsions reached approximately less than 50%. In addition, the results demonstrated that the maximum interaction effect between parameters was observed by adding 20-25 ppm of the demulsifier at 75 °C. Moreover, the demulsification efficiency was obtained by more than 75%. Meanwhile, the subsequent addition of the demulsifier to the crude oil emulsions at concentrations greater than 25 ppm has almost not changed the efficiency of the process. Finally, the numerical optimization results obtained by CCD indicated that the maximum separation efficiency of 80.65% was achieved under the following optimal conditions: demulsifier dosage at 25 ppm and temperature at 75 °C.