By driving monocyte chemotaxis, the chemokine receptor CCR2 shapes inflammatory responses and the formation of tumor microenvironments. This makes it a promising target in inflammation and immuno-oncology. Unfortunately, despite extensive efforts, no CCR2-targeting therapeutics have yet reached the clinic. Cited reasons include the redundancy of the chemokine system, suboptimal properties of compound candidates, and poor agreement of clinical responses with preclinical murine model studies. Structure-based drug design (SBDD) approaches can rationalize and greatly accelerate CCR2 compound discovery and optimization. The prerequisites for such efforts include a good atomic-level understanding of the molecular determinants of action of existing antagonists. In this study, using molecular docking and artificial intelligence- (AI-) powered compound library screening, we uncover the structural principles of small molecule antagonism and selectivity towards CCR2 and its sister receptor CCR5. We show that CCR2 orthosteric inhibitors universally occupy an inactive-state-specific tunnel between receptor helices 1 and 7; we also discover an unexpected role for an extra-helical groove accessible through this tunnel, suggesting its potential as a new targetable interface for CCR2 and CCR5 modulation. We implicate a single CCR2 residue, S101(2.63), as a determinant of CCR2/CCR5 and human/mouse antagonist selectivity, and corroborate its role through experimental gain-of-function mutagenesis. We systematically identify the binding determinants for various chemotypes of allosteric antagonists. We establish a critical role of induced fit in antagonist recognition, reveal strong chemotype selectivity of existing structures, and demonstrate the high predictive potential of a new deep-learning-based compound scoring function. Finally, we expand the available CCR2 structural landscape with computationally generated chemotype-specific models well-suited for structure-based antagonist design.