Objective: To discuss the relationship among air temperature, host evolutive phase (HEP) and host climatic qi(HCQ) by cosine curve model. Methods: All data were processed by R 3.2.0. The mean and standard of air temperatures in Beijing and Guangzhou including 60 years which group by date, HEP and HCQ were computed respectively. Then they were fitted by cosine curve model and analyzed by One-way ANOVA. At last, the temperatures in 2012-2014 were predicted. Results: The mean temperature of date, HEP and HCQ were well fitted by cosine curve model, all of adjust R~2 were above 0.95. According to Oneway ANOVA, there was no significant difference among celestial manager qi group and year evolutive phase group while in the same HEP or HCQ. The R~2 of predictions were above 0.94 and the real temperatures were almost in 95%CI. Conclusions: Cosine curve model could be used to fit the mean temperature of date, HEP and HCQ. The model could reflect some characteristics of HEP and the HCQ, such as the characteristics of stabilities, regionalism change, climatic change and period. And the models also supported the viewpoint that the origin of five evolutive phases and six climatic factors year was the Great Cold.