This paper investigates whether leverage effects and structural changes have positive effects on the volatility prediction of crude oil futures. On the basis of existing HAR models, this paper proposes three classes of new HAR models by considering leverage effects, structural changes, or both. The in‐sample and out‐of‐sample results show that leverage effects and structural changes contain significant information for predicting oil volatility. In most cases, structural changes have more in‐sample and out‐of‐sample incremental information than leverage effect, whereas leverage effects have more out‐of‐sample information for predicting 1‐day volatility. In addition, HAR models with leverage effects and structural changes have better in‐sample and out‐of‐sample performances than the corresponding other three classes of HAR models. The above results mean that leverage effects and structural changes should be considered while modelling and forecasting oil volatility.