Background and aims <p>Nonalcoholic fatty liver disease (NAFLD) is strongly associated with dietary habits and the gut microbiota. The dietary index for the gut microbiota (DI-GM) is a newly proposed index that reflects gut microbial diversity based on dietary intake. However, its relationship with NAFLD remains unclear. This study aimed to explore the association between DI-GM and the risk of NAFLD.</p> Methods <p>In this cross-sectional study, we utilized data from the NHANES 2009–2018. Multivariable logistic regression, restricted cubic spline curves (RCS), subgroup analysis, and mediation analysis were used to evaluate the association between DI-GM and the risk of NAFLD.</p> Results <p>A total of 4,923 participants were included in the study. According to the fully adjusted model, a significant inverse association was observed between DI-GM and NAFLD (OR = 0.883, <i>95% CI</i>: 0.835–0.932, <i>P</i> &lt; 0.001). After stratification by quartiles, compared with participants in the first quartile of DI-GM score, those in the fourth quartile had a 36.5% lower odds of developing NAFLD (OR = 0.635, <i>95% CI</i>: 0.481–0.839, <i>P</i> = 0.002). Mediation analysis revealed that 72.69% of the association between DI-GM and NAFLD was mediated by BMI (<i>P</i> &lt; 0.001). Subgroup analysis suggested that the association between DI-GM and NAFLD might be influenced by race (<i>P</i> for interaction &lt; 0.05). RCS analysis revealed a linear correlation between DI-GM and NAFLD (<i>P</i> for nonlinear = 0.883).</p> Conclusions <p>DI-GM is negatively associated with NAFLD risk, with BMI mediating this relationship and race being a significant influencing factor.</p>