OBJECTIVE: To assess racial and geographic disparities in antidiabetic medication discontinuation among Medicare beneficiaries with type 2 diabetes (T2D) in or around Diabetes Belt (DB) areas, with a specific focus on differences between non-Hispanic (NH) white and NH Black individuals. STUDY DESIGN: A retrospective cohort analysis was conducted on Medicare beneficiaries who initiated metformin and used antidiabetic medications during 2011-2015, including metformin, sulfonylureas, insulin, DPP-4 inhibitors, GLP-1 receptor agonists, SGLT2 inhibitors, and thiazolidinediones. Medication discontinuation was defined as a gap of 90 days or more without any antidiabetic medications. METHODS: Multivariable Cox regression was used to examine the influence of racial and geographic factors on medication discontinuation, controlling for demographic, socioeconomic, and contextual factors. The interaction between race and DB status was also examined. RESULTS: Among 21,159 Medicare beneficiaries initiating metformin during the study period, 8710 (41.2%) experienced medication discontinuation. NH Black individuals had a significantly higher discontinuation risk (HR: 1.22, 95% CI: [1.162, 1.286]) compared to NH White individuals. No significant geographic difference (HR: 1.02, 95% CI: [0.973, 1.072]) was observed between DB and Non-Diabetes Belt (NDB). NH Black patients consistently showed significantly higher discontinuation risks within both DB and NDB. No significant difference was found within the same race across counties. CONCLUSION: We found significant racial but no geographic disparities in antidiabetic medication discontinuation among Medicare beneficiaries with T2D. Further research is needed to understand the underlying factors to improve equitable diabetes care management.