Several relative risk models for survival time data in drug combination therapy are derived and their properties are discussed. The main intention of this paper is to clarify the differences among the models in order to help to choose the appropriate one in a given situation. The models are motivated by discussing their relation to well-known physiological concepts. In an example of two-drug treatment the models are compared with each other. For this chemotherapy animal survival study, dose-risk surfaces are fitted and optimal drug combinations are estimated. Methods for checking the model assumptions are mentioned.