Contraception allows couples to have their desired number of children by limiting or spacing women’s pregnancies. The use of contraceptives ultimately reduces maternal and child mortality, hence improve perinatal outcomes and child survival. In this study, multilevel logistic regression models are developed for investigating the hierarchical effects of contraceptive use and its selected determinants in Somaliland using the SLHDS 2020. A comparison between single-level and multilevel logistic regression models has been made to examine the likelihood of multilevel effects of contraceptive use. From the multilevel logistic regression model analysis, it was found that there is real multilevel variation among contraceptive users in Somaliland. The results indicate that a multilevel logistic regression model is the best fit over ordinary multiple logistic regression models. Only married women of reproductive age were considered in this study. (Descriptive statistics, binary logistic regression, and multilevel logistic regression were used for statistical analysis). The descriptive result revealed that only 7.3% of married women practiced contraception while 92.7 % did not practice contraception. Generally, this study revealed that women’s education, region. place of residence, occupation, desire for more children, knowledge of any contraceptives, and the number of living children were important factors that affect contraceptive use in Somaliland. The effect of regional and residence variation for these factors further implies that there exist considerable differences in contraceptive use among regions. Keywords: Contraceptive use, Multilevel logistic regression, Married women