OBJECTIVE: Social-cognitive models have been used to explain health risk behaviors in numerous populations, including people with HIV. However, these models generally do not account for the influence of clinically significant psychological problems such as major depression. DESIGN: This study examined whether a social-cognitive model would explain recent sexual transmission risk behavior among sexually active HIV-infected men who have sex with men (MSM) who meet or do not meet screening criteria for major depression. MAIN OUTCOME MEASURES: Participants (n = 403) completed self-report assessments of negative expectancy, social models, and self-efficacy (SE) related to condom use, as well as recent STRB and a screening measure for major depression. Multiple group modeling was used to examine whether condom use SE explained associations of negative expectancy and social models for condom use with recent STRB among participants who screened positive (n = 47) or negative (n = 356) for major depression. RESULTS: The multiple group model fit the data well (chi2(36) = 30.55, p = .73; CFI = 1.00; RMSEA<.01; SRMR = .05). Among MSM who screened negative for depression, lower condom use SE explained indirect paths from negative expectancy about condom use and poorer social models for condom use to greater STRB. Among MSM who screened positive for depression, only negative expectancy was associated with greater STRB. CONCLUSION: Models of STRB may not generalize to HIV-infected individuals with clinical depression. Risk reduction interventions based on these models should account for comorbid mental health conditions to maximize effectiveness.