OBJECTIVE: This study examined the medical utilization and cost experiences of ambulatory Medicaid- patients diagnosed with schizophrenia. METHODS: A historical cohort design was used. Eligible patients between 18 and 65 years were assigned to risperidone (N=1,438), clozapine (N=845), haloperidol (N=1,029), or other conventional antipsychotic (N=1,503) drug cohorts based on type of antipsychotic drug that was first used during a one-year window of time. Using an intent-to-treat approach, we report total and schizophrenia-related hospital, emergent care, drug, outpatient visit, laboratory use and cost experience based on paid claims data 6 months before and 12 months after the index date. Multiple regression analyses were used to determine the strength of the association of drug use with costs of care, controlling for demographic characteristics and baseline use of medical care services. RESULTS: Medical care service use declined 20% or more during the 12-month follow-up period. Schizophrenia-related costs comprised slightly over 70% of total costs for patients in the clozapine cohort, and slightly over 40% of total costs for the other cohorts. OLS regression explained approximately 50% of the variance in patient costs of care. Higher total and schizophrenia-related costs were associated with cost of care during baseline, clozapine use, risperidone use, number of months of antipsychotic drug use, and comorbidities. CONCLUSION: There were considerable differences in the use of medical services by patients with schizophrenia. Of the four cohorts examined, clozapine users had the fewest hospitalizations at baseline and during the follow-up period, but also the highest costs.