Bacterial vaginosis (BV) is a dysbiosis of the vaginal microbiome, characterized by low levels of lactobacilli and overgrowth of a diverse group of bacteria, associated with higher risk of a variety of infections, surgical complications, cancer, and preterm birth (PTB). Despite the lack of a consistently applicable etiology, Prevotella spp. are often associated with both BV and PTB, and Pr. bivia has known symbiotic relationships with both Peptostreptococcus anaerobius and Gardnerella vaginalis. Higher risk of PTB can also be predicted by a composite of metabolites linked to bacterial metabolism, but their specific bacterial source remains poorly understood. Here, we characterize diversity of metabolic strategies among BV-associated bacteria and lactobacilli and the symbiotic metabolic relationships between Pr. bivia and its partners and show how these influence the availability of metabolites associated with BV/PTB and/or pro- or anti-inflammatory immune responses. We confirm a commensal relationship between Pe. anaerobius and Pr. bivia, refining its mechanism, which sustains a substantial increase in acetate production. In contrast, the relationship between Pr. bivia and G. vaginalis strains, with sequence variant G2, is mutualistic, with outcome dependent on the metabolic strategy of the G. vaginalis strain. Taken together, our data show how knowledge of inter- and intraspecies metabolic diversity and the effects of symbiosis may refine our understanding of the mechanism and approach to risk prediction in BV and/or PTB. IMPORTANCE Bacterial vaginosis (BV) is the most common vaginal infection for women of childbearing age. Although 50% of women with BV do not have any symptoms, it approximately doubles the risk of catching a sexually transmitted infection and also increases the risk of preterm delivery in pregnant women. Recent studies of the vaginal microbiota have suggested that variation between species in the same genus or between strains of the same species explain better or poorer outcomes or at least some coexistence patterns for bacteria of concern. We tested whether such variation is manifested in how vaginal bacteria grow in the laboratory and whether and how they may share nutrients. We then showed that this affected the overall cocktail of chemicals they produce, including bacterially derived chemicals that we have previously shown are linked to a higher risk of preterm delivery.