Background: While mu-opioid agonists are effective in management of cancer-related pain, chronic opioid use may cause immunosuppression, which is hypothesized to interfere with the efficacy of immune checkpoint inhibitors (ICIs). There is limited evidence on how duration of opioid use affects outcomes in patients receiving ICIs. Methods: We identified 212 patients at the University of Illinois Hospital and Health Sciences System who received an ICI between January 1, 2015 and July 31, 2021. Through retrospective assessment, we measured the number of months a patient received opioids from the time an ICI was initiated until either death or the end of follow-up. Overall survival (OS) and progression-free survival (PFS) were compared between patients who received opioids for different durations of time, using Kaplan-Meier curves and log-rank tests. Multivariate Cox models were employed to estimate hazard ratios for different durations of opioids use, controlled for patient and disease factors such as Eastern Cooperative Oncology Group Performance Status (ECOG PS) and age. Results: Of the 212 patients, 87% had solid tumors with stage IV disease, 11% had solid tumors with stage II or III disease, and 1% had Hodgkin’s disease. The majority (58%) were African-American, 19% were white and non-Hispanic, 17% were Hispanic, and race or ethnicity was other or unknown for 7%. 45% did not receive opioids, 14% received opioids but for less than half the duration of follow-up, 5% received opioids for at least half the duration of follow-up but not the entire duration, and 36% received opioids for the entire duration of follow-up. 90% had an ECOG PS of 0-2, 8% had an ECOG PS of 3-4, and 2% did not have an ECOG PS recorded. 66% began receiving an ICI at age 60 or older while 34% began receiving an ICI at age 59 or younger. ECOG PS of 3-4 was associated with shorter OS compared to ECOG PS of 0-2 (6 months vs 29 months, p = 0.0061), and starting an ICI at age 59 or younger was associated with a shorter OS compared to age 60 or older (17 months vs 38 months, p = 0.0233). Multivariate analysis controlling for age and ECOG PS revealed that patients who received an opioid for the entire duration of follow-up had a shorter OS compared to those who received an opioid for less than the entire duration or not at all (hazard ratio 1.850, p = 0.0070). There was not a statistically significant difference in PFS between patients who received an opioid for the entire duration of follow-up and patients who received an opioid for less than the entire duration or not at all (hazard ratio 1.418, p = 0.1711). Conclusions: These results suggest that longer duration of opioid use is associated with shorter overall survival in patients receiving ICIs, even when controlling for the independent risk factors of age and ECOG PS. Further investigation, including prospective analysis, is needed to further validate this association.