1 The pharmacokinetics of parenteral mecillinam (n = 27) and oral pivmecillinam (n = 12) were studied in pregnant (n = 27) and non-pregnant (n = 12) subjects. 2 In early pregnancy (9-14 weeks of gestation) the mean peak plasma drug concentration (C(max) = 19 +/- 9-mu-g ml-1) after an intravenous injection of 200 mg mecillinam was significantly lower (P < 0.05) and the volume of distribution (V = 49 +/- 20 1) significantly larger (P < 0.05) than in non-pregnant subjects (C(max) = 35 +/- 18-mu-g ml-1, V = 29 +/- 12 1). In late pregnancy (39-40 weeks of gestation) the plasma mean peak concentration (C(max) = (29 +/- 14-mu-ml-1) after parenteral administration of 200 mg mecillinam was slightly lower and the volume of distribution (V = 65 +/- 29 1, V = 0.9 +/- 0.4 l kg-1) significantly larger than that in non-pregnant subjects (V = 0.4 +/- 0.3 l kg-1). Also after oral administration of 200 mg pivmecillinam, equimolar to 136.5 mg mecillinam, the mean peak plasma concentration in pregnant subjects (C(max) = 1.8 +/- 1.2-mu-g ml-1) was slightly lower than that in non-pregnant subjects (C(max) = 1.7 +/- 1.2-mu-g ml-1). 3 The mean half-life of elimination after parenteral administration of mecillinam was significantly longer during both early (t1/2,Z = 133 +/- 38 min, P < 0.05) and late pregnancy (t1/2,Z = 107 +/- 41 min, P < 0.05) as compared with the non-pregnant state (t1/2,Z = 75 +/- 21 min). After oral administration of pivmecillinam the elimination half-life was similar in pregnant (t1/2,Z = 57 +/- 34 min) and non-pregnant women (t1/2,Z = 61 +/- 32 min). 4 The transfer of mecillinam across the placenta was fast and it was detected in umbilical venous and arterial plasma, and in amniotic fluid. The ratio of umbilical venous plasma concentration to maternal plasma concentration in late pregnancy was 0.85. The ratios of amniotic fluid to maternal plasma drug concentration were 0.18 and 0.21 during early and late pregnancy after parenteral administration. 6 After parenteral administration of mecillinam its urinary recoveries in the first 8 h were 66% in early pregnancy, 72% in late pregnancy and 81% in the non-pregnant state. After oral administration 8 h urine recoveries were 28% and 39% in pregnant and non-pregnant states, respectively. 7 It is concluded that there is no need to increase the dosage of mecillinam or pivmecillinam during pregnancy.