Forecasting methods have wide applications in decision making. In the real world, rapid changes normally take place in different areas, specifically in financial markets. Collecting the required data is a main problem for forecaster in such unstable environments .The superiority of grey models over conventional forecasting model is that grey models require only a limited amount of data to predict behaviors of systems without knowing their mathematical models. This paper investigated Grey models for forecasting crude oil price and compared accuracy of models. The results obtained shows that operating of Rolling Grey and Grey M (1, 1) are better than another using models.