Fulminant hepatic failure (FHF) is one of the most challenging gastrointestinal emergencies encountered in clinical practice. Early identification of patients with FHF who need liver transplantation is very important. To construct a prediction model for the early diagnosis and prognosis of FHF, we studied the dynamics of metabolic intermediates and metabolic profiles with a D-galactosamine (GalN)/lipopolysaccharide (LPS)-treated BALB/c mouse model of FHF. Levels of plasma metabolites were quantified with gas chromatography/time-of-flight mass spectrometry, and data were processed with partial least squares discriminant analysis (PLS-DA). Distinct clustering differences were observed 5 and 6 hours after GalN/LPS treatment between mice that survived and those that died, but there were no differences between these groups 4 hours after treatment. Five hours after treatment, plasma levels of some metabolites differed significantly between the survival, dead, and control groups. Ketogenesis and the tricarboxylic acid cycle were inhibited in both the survival and dead groups, but in the dead group, the urea cycle was also inhibited, and glycolysis was elevated. PLS-DA indicated that principal component weighting was greatest for plasma levels of phosphate, beta-hydroxybutyrate, urea, glucose, and lactate. The Y-predicted scatter plot in the partial least squares (PLS) model assigned samples to the survival or dead groups with an a priori cutoff of 0.10 with 100% sensitivity and specificity. Similar results were observed in 11 FHF patients with different outcomes. In conclusion, the PLS model based on metabonomic analysis can be used to predict outcomes well, and plasma levels of phosphate, beta-hydroxybutyrate, urea, glucose, and lactate may constitute a set of markers for the early diagnosis and prognosis of FHF.