To evaluate the cost-effectiveness of Internet-based cognitive-behavioral therapy for bulimia nervosa (CBT-BN) compared to face-to-face delivery of CBT-BN. This study is a planned secondary analysis of data from a randomized clinical trial. Participants were 179 adults (98% female, mean age = 28 years) meeting DSM-IV criteria for bulimia nervosa who were randomized to group face-to-face or group Internet-based CBT-BN for 16 sessions during 20 weeks. The cost-effectiveness analysis was conducted from a third-party payor perspective, and a partial societal perspective analysis was conducted to investigate cost-utility (ie, cost per gain in quality-adjusted life-years) and patient out-of-pocket travel-related costs. Net health care costs were calculated from protocol and nonprotocol health care services using third-party payor cost estimates. The primary outcome measure in the clinical trial was abstinence from binge eating and purging, and the trial start and end dates were 2008 and 2016. The mean cost per abstinent patient at posttreatment was $7,757 (95% confidence limit [CL], $4,515, $13,361) for face-to-face and $11,870 (95% CL, $6,486, $22,188) for Internet-based CBT-BN, and at 1-year follow-up was $16,777 (95% CL, $10,298, $27,042) for face-to-face and $14,561 (95% CL, $10,165, $21,028) for Internet-based CBT-BN. There were no statistically significant differences between treatment arms in cost-effectiveness or cost-utility at posttreatment or 1-year follow-up. Out-of-pocket patient costs were significantly higher for face-to-face (mean [95% CL] = $178 [$127, $140]) than Internet-based ($50 [$50, $50]) therapy. Third-party payor cost-effectiveness of Internet-based CBT-BN is comparable with that of an accepted standard. Internet-based dissemination of CBT-BN may be a viable alternative for patients geographically distant from specialist eating disorder services who have an unmet need for treatment. ClinicalTrials.gov identifier: NCT00877786.