Though the advanced manufacturing capabilities offered by additive manufacturing (AM) have been known for several decades, industry adoption of AM technologies has been relatively slow. Recent advances in modeling and simulation of AM processes and materials are providing new insights to help overcome some of the barriers that have hindered adoption. However, these models and simulations are often application specific, and few are developed in an easily reusable manner. Variations are compounded because many models are developed as independent or proprietary efforts, and input and output definitions have not been standardized. To further realize the potential benefits of modeling and simulation advancements, including predictive modeling and closed-loop control, more coordinated efforts must be undertaken. In this paper, we advocate a more harmonized approach to model development, through classification and metamodeling that will support model composability, reusability, and integration. We review several types of AM models and use direct metal powder bed fusion characteristics to provide illustrative examples of the proposed classification and metamodel approach. We describe how a coordinated approach can be used to extend modeling capabilities by promoting model composability. As part of future work, a framework is envisioned to realize a more coherent strategy for model development and deployment.