BACKGROUND: Disparities among African Americans and Whites with severe mental illness have been identified in numerous studies. Yet it remains unknown if disparities are associated with race or other vulnerabilities common to this population. OBJECTIVES: This study used the Behavioral Model for Vulnerable Populations to examine mental health service utilization among 155 African Americans and Whites with severe mental illness for 12 months after discharge from a residential crisis program. DESIGN: This cross-sectional study was a secondary analysis of data from a randomized trial. RESULTS: Race did not emerge as a significant predictor of mental health service utilization. Factors associated with frequency of service use were diagnosis, age, drug use, gender, health benefit status, and enrollment in an outpatient mental health program. CONCLUSION: It is possible that the geographic location of the study, equal access to services, and equal rates of substance use between racial groups explain the lack of racial differences found in this sample.