Dual-energy X-ray absorptiometry (DEXA) has been used to assess body composition in dogs and cats in several studies, but studies are difficult to compare for several reasons. The aim of the present study was to evaluate whether positioning of dogs or cats in either dorsal or ventral recumbency during DEXA scanning influences results. Dogs and cats that were brought to the University Hospital for Companion Animals for euthanasia during the period 15 September–6 November 2015 were consecutively recruited if owners signed a written consent. Following euthanasia and before rigor mortis, the animals were body condition scored (BCS, nine-point scale) and DEXA scanned. DEXA measurements of total body mass (TBM), bone mineral content (BMC), bone mineral density (BMD), lean soft tissue mass (LSTM) and body fat (BF) were performed five times in ventral and two times in dorsal recumbency on each animal. Differences between positioning were analysed using Student's t test or Wilcoxon's test depending on normality of the data. A total of thirteen dogs and seven cats of different breeds, size, sexes and age were included. The CV for DEXA parameters in ventral or dorsal recumbency were, for dogs, TBM ≤ 0·1 %, BMC ≤ 1·63 %, BMD ≤ 1·29 %, LSTM ≤ 0·89 % and BF ≤ 1·52 %; and, for cats, TBM ≤ 0·08 %, BMC ≤ 0·61 %, BMD ≤ 0·49 %, LSTM ≤ 0·45 % and BF ≤ 0·88 %. In both positions, a good correlation was found for dogs (r 0·84–0·85; P < 0·0003) and cats (r 0·89–0·90; P < 0·0081) between the nine-point BCS system and BF percentage measured by DEXA. Ventral and dorsal recumbency provides comparable results, except that BMD measures were higher in dorsal recumbency (P < 0·0004).