The accelerated degradation test (ADT) is an efficient tool for assessing the lifetime information of highly reliable products. However, conducting an ADT is very expensive. Therefore, how to conduct a cost-constrained ADT plan is a great challenging issue for reliability analysts. By taking the experimental cost into consideration, this study proposes a semi-analytical procedure to determine the total sample size, testing stress levels, the measurement frequencies, and the number of measurements (within a degradation path) globally under a class of exponential dispersion (ED) degradation models. The proposed method provides more design insights for conducting an ADT plan, and it also speeds up the algorithm for determining the optimum planning by modifying the procedures in the traditional grid algorithm.