Rivaroxaban has been found to be noninferior to warfarin for preventing stroke or systemic embolism in patients with high-risk atrial fibrillation (AF) and is associated with a lower rate of intracranial hemorrhage. To assess the cost-effectiveness of rivaroxaban compared to adjusted-dose warfarin for the prevention of stroke in patients with AF, we built a Markov model using a United States payer/Medicare perspective and a lifetime time horizon. The base-case analysis assumed a cohort of patients with AF 65 years of age with a congestive heart failure, hypertension, age, diabetes, stroke (2 points) score of 3 and no contraindications to anticoagulation. Data sources included the Rivaroxaban Once-daily Oral Direct Factor Xa Inhibition Compared with Vitamin K Antagonism for Prevention of Stroke and Embolism Trial in Atrial Fibrillation (ROCKET-AF) and other studies of anticoagulation. Outcome measurements included costs in 2011 United States dollars, quality-adjusted life years (QALYs), and incremental cost-effectiveness ratios (ICERs). Patients with AF treated with rivaroxaban lived an average of 10.03 QALYs at a lifetime treatment cost of $94,456. Those receiving warfarin lived an average of 9.81 QALYs and incurred costs of $88,544. The ICER for rivaroxaban was $27,498 per QALY. These results were most sensitive to changes in the hazard decrease of intracranial hemorrhage and stroke with rivaroxaban, cost of rivaroxaban, and time horizon. Monte Carlo simulation demonstrated rivaroxaban was cost-effective in 80% and 91% of 10,000 iterations at willingness-to-pay thresholds of $50,000 and $100,000 per QALY, respectively. In conclusion, this Markov model suggests that rivaroxaban therapy may be a cost-effective alternative to adjusted-dose warfarin for stroke prevention in AF.