Adenosine is widely used as a vasodilator agent in myocardial perfusion imaging. Caffeine inhibits the effect, but the time of caffeine abstinence needed is under discussion and varies from 12 to 24h. Therefore, our aim was to examine whether the time of caffeine abstinence affects the hyperaemic response using quantification of coronary sinus flow (CS F) with cardiac magnetic resonance (CMR) during adenosine infusion. Healthy individuals (n=16, eight females, age 41±3years) underwent two CMR examinations with 12 and 24h of caffeine abstinence. CS F was quantified with phase-contrast velocity mapping (PC-)CMR during adenosine infusion (140μgkg(-1) min(-1) ) and rest and the CS F reserve between adenosine and rest was calculated. Myocardial perfusion (MP) was calculated as CS F×heart rate/left ventricular mass. Cardiac output (CO) was quantified using PC-CMR of the ascending aorta. The CS F reserve was lower after 12h abstinence compared to 24h (4·31±0·57 versus 5·32±0·76, P=0·03). In six of 16 subjects (38%), CS F reserve was >30% higher with longer caffeine abstinence. MP during adenosine was lower after 12h compared to 24h caffeine abstinence (3·59±0·37 versus 4·23±0·28 mlmin(-1) g(-1) ; P=0·046). The increase in CO during adenosine between the two occasions did not differ (55±7% and 55±6%, P=0·11). Interobserver variability for CS F/heartbeat was -0·05±1·00ml. Hyperaemia during adenosine is lower in some patients with 12h of caffeine abstinence compared to 24h. Longer caffeine abstinence, that is 24h, is of value before pharmacological stress testing as the individual response is not known and the individual variation is large.