OBJECTIVE The aim of this retrospective study was to investigate whether self-reported allergy to penicillin may contribute to a higher rate of postsurgical infection and implant failure. METHOD AND MATERIALS This retrospective, non-interventional, open cohort study reports on implant survival and infection complications of 5,576 implants placed in private practice by one periodontist, and includes 4,132 implants that were followed for at least 1 year. Logistic regression was applied to examine the relationship between self-reported allergy to penicillin and implant survival, while controlling for potential confounders such as smoking, implant site, bone augmentation, loading protocol, immediate implantation, and bone level at baseline. The cumulative survival rate (CSR) was calculated according to the life table method and the Cox proportional hazard model was fitted to data. RESULTS Out of 5,106 implants placed in patients taking penicillin it was found that 0.8% failed, while 2.1% failed of the 470 implants placed for patients with self-reported allergy to penicillin (P = .002). Odds of failure for implants placed in penicillin-allergic patients were 3.1 times higher than in non-allergic patients. For immediate implant placement, penicillin-allergic patients had a failure rate 10-times higher than the non-allergic cohort. Timing of implant failure occurring within 6 months following implantation was 80% in the penicillin-allergic group versus 54% in the non-allergic group. From the 48 implant sites showing postoperative infection: penicillin-allergic patients had an infection rate of 3.4% (n = 16/470) versus 0.6% in the non-allergic group (n = 32/5,106) (P < .05). CONCLUSION Self-reported penicillin allergy was associated with a higher rate of infection, and primarily affected early implant failure.