The objective of the study was to determine a prediction equation of body weight of Amazonian manatee calves in captivity using their biometry. It was conducted out with 7 calves (4 males and 3 females) of approximately 8 months of age and average body weight of 29.94 ± 0.055 kg, arranged in pools of sufficient size. Biometry and weighing were performed periodically, with the following measurements: body weight (BW), total curved length (TCL), total length (TL), circumference (CIR), fin width (FW), tail width (TW) and peduncle (PED). Data were subjected to Pearson correlation analysis and linear regression, using the statistical software IBM SPSS 24.0. The results showed a significant correlation (P < 0.05) between BW and TCL, TL, FW, TW, CIR and PED. Six linear simple regression equations were generated with relation to BW, using as predictor variables those that showed positive correlation. The CIR equation independent variable had the highest correlation coefficient and less error estimate (R² = 0.855, R²_aj = 0.852). In addition, three linear multiple regression equations of BW were calculated using the predictor variables previously analyzed by Person correlation analysis. The equation that used all biometric measurements (TCL, TL, FW, TW, CIR and PED) had the highest coefficient of determination and the lowest estimation error to predict BW. In conclusion, the biometric measurements of TCL, TL, FW, TW, CIR and PED showed a high correlation with the BW and can be used as predictive variables of BW of manatee calves, as they are easy to be measured.