Objective: To examine the association between estimated cardiorespiratory fitness (eCRF) and incident stroke by black and white race. Participants and Methods: A total of 24,162 participants from the REasons for Geographic And Racial Differences in Stroke study (13,232 [54.8%] women; 9543 [39.5%] blacks; mean age, 64.6±9.3 years) without stroke at enrollment between January 15, 2003, and October 30, 2007, were followed for incident stroke through March 31, 2016. Baseline eCRF in maximal metabolic equivalents was determined using nonexercise sex-specific algorithms and further grouped into age- and sex-specific tertiles. Results: Over a mean of 8.3±3.2 years of follow-up, 945 (3.9%) incident strokes occurred (377 in blacks and 568 in whites). The association between eCRF and stroke risk differed significantly by race (P Interaction <.001). In whites, after adjustment for stroke risk factors and physical functioning score, the hazard ratio of stroke was 0.82 (95% CI, 0.67-1.00) times lower in the middle tertile of eCRF than in the lowest tertile and was 0.54 (95% CI, 0.43-0.69) times lower in the highest tertile of eCRF. The protective effect of higher levels of eCRF on stroke incidence was more pronounced in those 60 years or older among whites. No association between eCRF and stroke risk was observed in blacks. Conclusion: Estimated cardiorespiratory fitness measured using nonexercise equations is a useful predictor of stroke in whites. The lack of an overall association between eCRF and stroke risk in blacks suggests that the assessment of eCRF in blacks may not be helpful in primary stroke prevention.