Objective: To compare time to all-cause discontinuation (TTAD) across alternative antipsychotics in the treatment of schizophrenia. Methods: Data from a commercial health plan from July 1, 2003 to June 30, 2006 were used to identify non-institutionalized patients with schizophrenia (ICD-9 codes 295.xx) who initiated treatment using a typical antipsychotic (TAP), atypical antipsychotic (AAP: aripiprazole, olanzapine, quetiapine, risperidone or ziprasidone), mood stabilizer or antidepressant. Episodes were divided into three categories: restarting treatment after a break in drug therapy >15 days with the drug used in the previous episode, switching therapy with or without a break in treatment, and augmentation therapy. First observed episodes were excluded from the analysis due to uncertainty concerning the patient's prior treatment history. A total of 21,872 episodes were included in the analyses using ordinary least squares (OLS) regression models of TTAD adjusting for age, gender, geographic region, drug use history, prior medical care use, schizophrenia diagnosis and co-morbid medical conditions. Results: Only 39.3% of all episodes involved an antipsychotic. Antipsychotics were used predominately as augmentation therapy (55%) with the remaining episodes of antipsychotic drug therapy evenly divided between restart (23%) and switching (22%) episodes. Unadjusted mean TTAD in days on initial therapy measured across all episode types was 172 for TAP and risperidone; 177 for olanzapine; 180 for antidepressants; 196 for mood stabilizers; 202 for quetiapine; 206 for aripiprazole; and 213 for ziprasidone. We estimated that TTAD on initial therapy was shorter for AAP patients restarting therapy relative to TAP patients (range +2 to -33 days), but generally longer for AAP patients switching therapies (range -14 to +27 days). Three AAPs displayed significantly longer TTAD in augmentation: +23 days for quetiapine (p<0.05); +43 days for aripiprazole (p<0.0001) and +56 days for ziprasidone (p<0.0001). Conclusion: In a commercially-insured population, AAPs are associated with longer TTAD than TAPs in augmentation therapy.