Non-small cell lung cancer (NSCLC) is a leading cause of cancer-related deaths worldwide. Immunotherapy, particularly PD-1 inhibitors, has revolutionized the treatment landscape for NSCLC. However, the predictive biomarkers for PD-1 inhibitor therapy are still limited. Serum cytokines have emerged as potential biomarkers for predicting treatment outcomes. This meta-analysis aims to investigate the predictive value of serum cytokines in PD-1 inhibitor therapy for NSCLC. We conducted a comprehensive literature search in major databases, including PubMed, Google scholar, Embase, and Cochrane database, with a focus on literature published up until October 22, 2024. Studies investigating the association between serum cytokine levels and treatment outcomes in NSCLC patients receiving PD-1 inhibitor therapy were included. The primary outcomes were progression-free survival (PFS) and overall survival (OS). The meta-analysis revealed that elevated IL-6 levels were significantly associated with poorer PFS in NSCLC patients (HR = 2.30, 95% CI [1.39-3.80], P = 0.001). Additionally, high IL-10 expression was related to poorer PFS in NSCLC after therapy (HR = 2.45, 95% CI [1.26-4.76], P = 0.009). In contrast, no significant associations were found between OS and the expression of various cytokines, including IL-4, IL-5, IL-6, IL-8, IL-10, IFN-γ, IL-1β, TNF-α, and IL-12p70. This meta-analysis demonstrates that elevated IL-6 and IL-10 levels are significantly associated with poorer PFS in NSCLC patients receiving PD-1 inhibitor therapy. These findings suggest that serum cytokine levels may serve as predictive biomarkers for treatment outcomes. Further studies are needed to validate these results and explore the underlying mechanisms.