Aims The objective of this study was to estimate the risk of acute liver injury associated with individual acid‐suppressing drugs and assess the role of dose and duration of treatment. Methods We used a nested case‐control study design within a cohort of over 100 000 users of cimetidine, famotidine, omeprazole and ranitidine. The primary source of information was the General Practitioners Research Database. We identified 108 981 persons aged 20–74 years who received at least one prescription for cimetidine, famotidine, omeprazole, or ranitidine during 1990–93, and we ascertained the first occurrence of clinically acute liver injury referred to a specialist or admitted to a hospital. Results After review of medical records, 33 patients were considered eligible cases of idiopathic acute liver injury with no fatal cases. The type of liver injury was hepatocellular in almost half of the cases, and 80% of all cases presented with jaundice. Twelve cases occurred among current users of cimetidine, five among ranitidine users and one in an omeprazole user. The absolute risk of acute liver injury associated with cimetidine was estimated to be slightly greater than one per 5000 users of cimetidine. The adjusted relative risk (RRs) and 95% CI of developing acute liver injury associated with current use of cimetidine compared to non‐use was 5.5 (1.9–15.9), with omeprazole 2.1 (0.2–19.2) and with ranitidine 1.7 (0.5–5.8). In the absence of concomitant use of other hepatotoxic drugs, the RR with cimetidine was 14.4 (2.8–73.7). Among users of cimetidine, the risk was especially high in the first 2 months of starting therapy (RR: 11.3, 3.7–35.1) and at daily doses of 800 mg or greater (RR: 8.8, 3.0–26.0). Conclusions Cimetidine was the individual anti‐ulcer drug with the highest risk of developing symptomatic acute liver disease. Further data are required to confirm this finding. Our study indicates that there is a dose relationship and a short latent period between cimetidine treatment and acute liver injury.