Tourism e-commerce live streaming has become a vital marketing tool for travel businesses, yet sustaining user engagement remains challenging. This study aims to explore how perceptual elements in live streaming influence users’ value co-creation behaviors, with perceived value as a mediating factor. Guided by the Stimulus-Organism-Response (SOR) framework, a conceptual model was developed linking perceptual elements (information content, interactivity, and host characteristics), perceived value (functional, emotional, social), and value co-creation behaviors (participation and citizenship). Based on a survey of 472 live stream viewers in Henan Province, data were analyzed using structural equation modeling and the PROCESS macro. Results show that interactivity and host characteristics significantly enhance co-creation through increased perceived value, while information content shows no effect on social value and host characteristics do not influence functional value. Mediation analysis confirms perceived value as a partial mediator. The findings highlight the importance of perceived value in converting perceptual stimuli into co-creation outcomes. Practically, tourism e-commerce platforms should foster co-creation by enhancing content quality, integrating gamified and interactive features, and training professional hosts to stimulate user engagement.