We investigate the causal impact of prenatal exposure to air pollution on neonatal health in Italy in the 2000s. Our empirical setting combines detailed information on mother’s residential location from birth certificates with PM10 concentrations from air pollution monitors. We exploit variation in rainfall shocks to instrument for non-random air pollution exposure. Average PM10 and the number of days with PM10 concentration above the hazard limit reduce birthweight, gestational age, and measures of overall newborn health. The effects are largest for third trimester exposure and for low-income and less educated mothers.