Aim Vascular congestion may lead to an increase of carbohydrate antigen 125 (CA‐125). The role of CA‐125 as a biomarker of congestion or for prognosis across the full ejection fraction (EF) spectrum of chronic heart failure (HF) remains unknown. Methods and results Serum CA‐125 was measured in 1111 study participants from the EMPEROR‐Reduced and EMPEROR‐Preserved trials. Congestive signs and symptoms were evaluated across CA‐125 tertiles. Cox regression was used to study the association with outcomes. The primary outcome was a composite of first HF hospitalization or cardiovascular (CV) death. No significant association was present between baseline CA‐125 levels and congestive signs or symptoms. In the overall population, higher CA‐125 levels were not associated with an increased risk of primary outcome (tertile 3 vs. tertile 1: hazard ratio [HR] 1.34; 95% confidence interval [CI] 0.91–1.96; p ‐trend = 0.11). However, higher CA‐125 levels were associated with an increased risk of primary outcome in patients with HF and reduced EF (HFrEF; tertile 3 vs. tertile 1: HR 2.25 [95% CI 1.30–3.89]), but not among patients with preserved EF (HFpEF; tertile 3 vs. tertile 1: HR 0.68 [95% CI 0.38–1.21]); interaction‐ p = 0.02). Patients in the upper CA‐125 tertile also showed the steepest estimated glomerular filtration rate decline over time ( p ‐trend = 0.03). The effect of empagliflozin to reduce the risk of CV death or HF hospitalization appeared to be attenuated in those with lower baseline CA‐125 levels (interaction‐ p ‐trend = 0.09). Conclusion Across the range of EF in patients with chronic HF enrolled in the EMPEROR trials, the majority of whom did not have clinical evidence of congestion, CA‐125 concentrations were not significantly associated with congestive signs or symptoms. CA‐125 concentrations may predict HF hospitalization/CV death in patients with HFrEF, but not those with HFpEF. Clinical Trial Registration: EMPEROR‐Reduced (NCT03057977), EMPEROR‐Preserved (NCT03057951).