CONTEXT: Concerns about mental health recovery persist after the 2005 Gulf storms. We propose a recovery model and estimate costs and outcomes. OBJECTIVE: To estimate the costs and outcomes of enhanced mental health response to large-scale disasters using the 2005 Gulf storms as a case study. DESIGN: Decision analysis using state-transition Markov models for 6-month periods from 7 to 30 months after disasters. Simulated movements between health states were based on probabilities drawn from the clinical literature and expert input. SETTING: A total of 117 counties/parishes across Louisiana, Mississippi, Alabama, and Texas that the Federal Emergency Management Agency designated as eligible for individual relief following hurricanes Katrina and Rita. PARTICIPANTS: Hypothetical cohort, based on the size and characteristics of the population affected by the Gulf storms. Intervention Enhanced mental health care consisting of evidence-based screening, assessment, treatment, and care coordination. MAIN OUTCOME MEASURES: Morbidity in 6-month episodes of mild/moderate or severe mental health problems through 30 months after the disasters; units of service (eg, office visits, prescriptions, hospital nights); intervention costs; and use of human resources. RESULTS: Full implementation would cost $1133 per capita, or more than $12.5 billion for the affected population, and yield 94.8% to 96.1% recovered by 30 months, but exceed available provider capacity. Partial implementation would lower costs and recovery proportionately. CONCLUSIONS: Evidence-based mental health response is feasible, but requires targeted resources, increased provider capacity, and advanced planning.