Objectives: To investigate the relationship between the first trimester microbiome, inflammation, and small vulnerable newborns (SVN). Setting: Rural low, middle-income country: Bangladesh Population: 213 pregnant women were enrolled during the first trimester of pregnancy as part of the NICHD Global Network for Women’s and Children’s Health registry, Bangladesh. Methods: Blood and stool samples were collected at enrollment and birth outcomes within 72 hours of delivery. Using random forest machine learning models, whether the first-trimester maternal microbiome predicted SVN was evaluated. Main outcome measures: Small vulnerable newborns (born preterm, low birth weight, or small for gestational age). Results: The birth outcome SVN could be discriminated from non-SVN using a microbiome-trained random forest model (AUC = 0.653, 95% CI 0.518-0.789) supporting that the microbiome can influence gestation and fetal development. The microbiome also predicted the inflammatory markers plasma alpha-1-acid glycoprotein and fecal calprotectin (AUC = 0.742, 95% CI: 0.616-0.868 and AUC = 0.793, 95% CI: 0.680-0.905, respectively), while micronutrient concentrations, anemia, C-reactive protein, and the presence of atypical Enteropathogenic E. coli were not reliably predicted. Connecting inflammation to SVN, it was found that higher α-1-acid glycoprotein was significantly associated with SVN (logistic regression: aOR = 1.98; 95% CI: 1.04-3.85) whereas no significant association between calprotectin and SVN was observed. Conclusions: Together, these findings support that the first-trimester maternal gut microbiome contributes to SVN via induction of chronic systemic inflammation but not micronutrient absorption and demonstrates that the pathogenesis of SVN starts as early as the first trimester.