It remains uncertain whether air pollution modifies the magnitude and time course of the temperature mortality association. We applied a distributed lag non-linear model (DLNM) combined with non-linear interaction terms to assess the modifying effects of particulate matter with an aerodynamic diameter of 10 mm or less (PM(10)) on the association between mean temperature and mortality in Guangzhou, China.We found that both cold and hot effects increased with the quartiles of PM(10). The elderly were more vulnerable to cold and hot effects. Men suffered more from cold-related mortality than women, with the gender difference enlarging with the quartiles of PM(10). We identified statistically significant interaction effects between PM(10) and mean temperature on mortality (except for respiratory mortality). Cold and hot effects basically appeared acutely on highly polluted days, while effects were delayed on lowly polluted days. The findings indicate the importance of reducing PM(10) emission on extremely temperature days.