The objective of this study was to evaluate the cost-effectiveness of an HIV prevention intervention for gay and bisexual male adolescents. The intervention included individualized risk assessment and counseling, peer education, optional HIV testing, and referrals to needed services. From 1989 to 1994, 501 male volunteers, 13 to 21 years of age, who self-identified as gay/bisexual or as having had sex with men, completed preintervention and postintervention surveys to assess changes in HIV risk behavior. An HIV transmission model was constructed to project the HIV seroprevalence in the target population over a 10-year period from the self-reported number of partners for unprotected anal intercourse. Cost-effectiveness was analyzed from a societal perspective. Total costs of the intervention, including medical treatment costs saved, were projected to be $1.1 million U.S. for the 10-year period. The number of HIV infections averted and the quality-adjusted life years (QALYs) saved were projected to be 13 and 180, respectively. An incremental cost-effectiveness ratio was projected to be $6180 U.S. per QALY saved. The intervention was found to be cost-effective from the societal perspective. In addition, HIV prevalence in the target population was projected to be 6.1% without and 5.6% with intervention by the end of the 10-year period. This study highlights that an HIV prevention program can be cost-effective even if the effects on behavior are partial and short term.