Although the combined treatment of surgery, radiotherapy, chemotherapy, and emerging target therapy has significantly improved the outcomes of patients with head and neck cancer, distant metastasis remains the leading cause of treatment failure. In this study, we propose a deep learning-based multimodal framework integrating CT imaging, radiomics, and clinical data to predict metastasis risk in HNSCC. A total of 1497 patients were retrospectively analyzed. Tumor and organ masks were generated from pretreatment CT scans, from which a 3D Swin Transformer extracted deep imaging features, while 1562 radiomics features were reduced to 36 via correlation filtering and random forest selection. Clinical data (age, sex, smoking, and alcohol status) were encoded and fused with imaging features, and the multimodal representation was fed into a fully connected network for prediction. Five-fold cross-validation was used to assess performance via AUC, accuracy, sensitivity, and specificity. The multimodal model outperformed all single-modality baselines. The deep learning module alone achieved an AUC of 0.715, whereas multimodal fusion significantly improved performance (AUC = 0.803, ACC = 0.752, SEN = 0.730, SPE = 0.758). Stratified analyses confirmed good generalizability across tumor subtypes. Ablation experiments demonstrated complementary contributions from each modality, and the 3D Swin Transformer provided more robust representations than conventional architectures. This multimodal deep learning model enables accurate, non-invasive metastasis prediction in HNSCC and shows strong potential for individualized treatment planning.