STUDY OBJECTIVE: To explore the effects of metformin dose on cancer risk reduction in patients with type 2 diabetes. DESIGN: Population-based cohort study. DATA SOURCE: National Health Insurance program Longitudinal Health Insurance Database. PATIENTS: A total of 65,754 age- and gender-matched patients without diabetes and no previous cancer diagnosis were extracted from the database. MEASUREMENTS AND MAIN RESULTS: We compared cancer risk among the subjects who had no diabetes, had type 2 diabetes but were not on diabetes drugs, used metformin only, used antidiabetic drugs other than metformin, or used metformin in combination with other antidiabetic drugs. Our results revealed dose-dependent effects of metformin on cancer risk and cancer onset times. A significant decrease in cancer risk was found in the monotherapy group who received more than 360 defined daily doses (DDDs) of metformin (hazard ratio [HR] 0.40, 95% confidence interval [CI] 0.24–0.66). The greatest decrease in cancer risk was observed in patients who took more than 1080 DDDs (HR 0.27, 95% CI 0.09–0.84). Significantly greater dose-dependent effects were seen in patients who used metformin in combination with other antidiabetic drugs. CONCLUSION: The magnitude of cancer risk reduction and prolonged cancer onset times produced by metformin in patients with type 2 diabetes depended on the dose of metformin, regardless of whether metformin was used alone or combined with other antidiabetic drugs.