To determine predictors and outcomes of extubation failure in extremely preterm (EP) infants born <28 weeks' gestational age (GA). Retrospective clinical audit across two tertiary-level neonatal intensive care units in Melbourne, Australia. Two-hundred and four EP infants who survived to their first extubation from mechanical ventilation. Extubation failure (re-intubation) within 7 days after the first extubation. Lower GA (odds ratio [OR] 0.71, 95% confidence interval (CI), 0.61-0.89, P < 0.001) and higher pre-extubation measured mean airway pressure (MAP) on the mechanical ventilator (OR 1.9 [95% CI 1.41-2.51], P < 0.001) predicted extubation failure. The area under a receiver operating characteristic curve for GA and MAP was 0.77 (95% CI 0.70-0.82). After adjustment for GA, infants who experienced extubation failure had higher rates of bronchopulmonary dysplasia (P < 0.001), post-natal systemic corticosteroid treatment (P < 0.001), airway trauma (P < 0.003), longer durations of treatment with mechanical ventilation (P < 0.001), non-invasive respiratory support (P < 0.001), supplemental oxygen therapy (P = 0.05) and longer hospitalisation (P = 0.025). Lower GA and higher pre-extubation measured MAP were predictive of extubation failure within 7 days in extremely preterm infants. Extubation failure was associated with increased morbidity and extended periods of respiratory support and hospitalisation.