Increased dietary Na intake and decreased dietary K intake are associated with higher blood pressure. It is not known whether the dietary Na:K ratio is associated with all-cause mortality or stroke incidence and whether this relationship varies according to race. Between 2003 and 2007, the REasons for Geographic And Racial Differences in Stroke (REGARDS) cohort enrolled 30 239 black and white Americans aged 45 years or older. Diet was assessed using the Block 98 FFQ and was available on 21 374 participants. The Na:K ratio was modelled in race- and sex-specific quintiles for all analyses, with the lowest quintile (Q1) as the reference group. Data on other covariates were collected using both an in-home assessment and telephone interviews. We identified 1779 deaths and 363 strokes over a mean of 4·9 years. We used Cox proportional hazards models to obtain multivariable-adjusted hazard ratios (HR). In the highest quintile (Q5), a high Na:K ratio was associated with all-cause mortality (Q5 v. Q1 for whites: HR 1·22; 95 % CI 1·00, 1·47, P for trend = 0·084; for blacks: HR 1·36; 95 % CI 1·04, 1·77, P for trend = 0·028). A high Na:K ratio was not significantly associated with stroke in whites (HR 1·29; 95 % CI 0·88, 1·90) or blacks (HR 1·39; 95 % CI 0·78, 2·48), partly because of the low number of stroke events. In the REGARDS study, a high Na:K ratio was associated with all-cause mortality and there was a suggestive association between the Na:K ratio and stroke. These data support the policies targeted at reduction of Na from the food supply and recommendations to increase K intake.