Objective To report on the cost‐effectiveness of the Exercise for Health trial, comparing an exercise intervention with usual care during and following treatment for women with breast cancer. Methods Women with breast cancer were randomized to an 8‐month exercise intervention (involving regular contact with an exercise physiologist over the phone, n = 67, or home delivered face to face, n = 67) or usual care (n = 60) group and were assessed pre‐intervention (5 weeks post‐surgery), mid‐intervention (6 months post‐surgery), and 10 weeks post‐intervention (12 months post‐surgery). The benefit measures were “number of improvers” in quality of life (FACT‐B+4) and quality‐adjusted life years (QALYs). Data on provider, patient, and government costs were used to consider 2 cost scenarios: (1) a service provider model and (2) a private model. Results There were 69 improvers in the intervention group compared with 21 in the usual care group (odds ratio 2.09, 95% confidence interval 1.08, 4.01; P = .033). The incremental cost per improver was A$2282 to A$2644. Quality‐adjusted life years gain for the intervention group versus the usual care group was 0.009, with incremental cost per QALY gain for models 1 and 2 being A$105 231 and A$90 842, respectively. However, sensitivity analyses indicate that incremental cost per QALY gained was volatile to EuroQol‐5D‐3L weights. Conclusions Findings suggest that a pragmatic exercise intervention yields more women with markedly improved quality of life after breast cancer than usual care and may be cost‐effective. The results are less certain in terms of incremental cost per quality‐adjusted life years; however, this may be an inappropriate measure for reflecting exercise benefit for women with breast cancer.