This position paper explores pluri-perspectivism as a core element of human creative experience and its relevance to human–robot co-creativity. We propose a layered, five-dimensional model to guide the design of co-creative behaviors and the analysis of interaction dynamics. This model is based on literature and results from an interview study we conducted with 10 visual artists and 8 arts educators, examining how pluri-perspectivism supports creative practice. The findings of this study provide insight how robots could enhance human creativity through adaptive, context-sensitive behavior, demonstrating the potential of pluri-perspectivism. This paper outlines future directions for integrating pluri-perspectivism with vision-language models (VLMs), to support context sensitivity in co-creative robots.