The elimination of caffeine was investigated in a 1860 g, 31 week gestation neonate, following the accidental administration of a 160 mg.kg-1 dose. The first serum concentration measured was 217.5 mg.l-1 at 36.5 h after dosing. Fitting of time-concentration data was performed using non-linear regression with MKMODEL. A first order elimination model was superior to a mixed order model. Parameter estimates were: clearance 0.01 l.h-1, volume of distribution 1.17 litres, elimination half-life 81 h. Toxic manifestations included hypertonia, sweating, tachycardia, cardiac failure, pulmonary oedema and metabolic disturbances (metabolic acidosis, hyperglycaemia and creatine kinase elevation). An unusual feature of this infant's illness course was gastric dilatation. These signs resolved by day 7 at a serum concentration of 60-70 mg.l-1. Caffeine clearance has traditionally been reported as either an absolute value or as directly proportional to body weight. The per kilogram model gives an erroneous impression that clearance is greatest in early childhood and then decreases with age until adult rates are reached in late adolescence. Age-related clearance values reported in the literature were reviewed using an allometric 3/4 power model. This size model demonstrates that clearance increases in infancy and reaches adult rates within the first three months of life.