Aim Cytokines released from chronically‐activated microglia could result in neuroinflammation. An accurate profile of the relationship between cytokines and Alzheimer's disease (AD) pathogenesis, as well as the patterns of these inflammatory mediators in AD patients could lead to the identification of peripheral markers for the disease. The present study was undertaken to identify pro‐ and anti‐inflammatory cytokines associated with AD in the Malaysian population. Methods Further to informed consent from 39 healthy subjects and 39 probable AD patients, 8.5 mL of peripheral blood was collected and serum was extracted. The differential levels of 12 serum cytokines extracted from peripheral blood samples were measured using Procarta Multiplex Cytokine and enzyme‐linked immunoassay kits. Concentrations of cytokines were measured at 615 nm using a fluorometer. Results Except for tumor necrosis factor‐α, all classical pro‐inflammatory cytokines (interleukin [IL]‐1β, IL‐6, IL‐12 and interferon‐γ) were found to be significantly upregulated (P < 0.001) in AD patients. Three of the five non‐classical pro‐inflammatory cytokines (C‐X‐C motif ligand 10 [CXCL‐10], monocyte chemoattractant protein‐1 and macrophage inflammatory protein‐1α) showed similar patterns. Both classical IL‐10 and non‐classical IL‐13 anti‐inflammatory cytokines were significantly downregulated (P < 0.001) in AD patients when compared with non‐AD controls. Receiver operating characteristic curve analyses for both CXCL‐10 (IP‐10) and IL‐13 showed a high level of diagnostic accuracy (area under curve = 1 [95% confidence interval]). Both CXCL‐10 and IL‐13 also showed sensitivity of 100% and specificity of 100% for diagnosis of AD (cut‐off values >53.65 ρg/mL and <9.315 ρg/mL, respectively). Conclusions Both the non‐classical pro‐inflammatory CXCL‐10 and anti‐inflammatory IL‐13 cytokines showed promising potential as blood‐based cytokine biomarkers for AD. This is the first study of non‐classical cytokine profiles of Malaysian AD patients. Geriatr Gerontol Int 2017; 17: 839–846.