AIMS: Sodium-glucose cotransporter 2 inhibitors (SGLT-2is) have been demonstrated to be associated with cancer cell mechanisms. However, whether they increase the risk of cancer remains unclear. Thus, this study aimed to determine the association between SGLT-2i use and the incidence of cancer in patients with diabetes mellitus (DM) in Taiwan. MATERIALS AND METHODS: This retrospective cohort study was based on the Taiwan National Health Insurance database. The study population comprised patients with DM, and those who first used SGLT-2is during 2016-2018 were assigned to the study group. Greedy propensity score matching was performed to select patients who first used dipeptidyl peptidase 4 inhibitors (DPP-4is), and these patients were assigned to the control group. A Cox proportional hazards model was used to estimate the adjusted hazard ratios (aHRs) and 95% confidence intervals (CIs) for cancer risk in the study and control groups; this model was adjusted for demographic characteristics, DM severity, comorbidities and concomitant medication use. RESULTS: After controlling for relevant variables, the SGLT-2i cohort (aHR = 0.90, 95% CI = 0.87-0.93) had a significantly lower risk of developing cancer than the DPP-4i cohort, particularly when the SGLT-2i was dapagliflozin (aHR = 0.91, 95% CI = 0.87-0.95) or empagliflozin (aHR = 0.90, 95% CI = 0.86-0.94). Regarding cancer type, the SGLT-2i cohort's risk of cancer was significantly lower than that of the DPP-4i cohort for leukaemia, oesophageal, colorectal, liver, pancreatic, lung, skin and bladder cancer. CONCLUSIONS: SGLT-2i use was associated with a significantly lower risk of cancer than DPP-4i use.