The major difficulty of prosody modeling and automatic tone recognition of continuous Mandarin speech is the complex interaction of tones and prosody/intonation on F0 contours. In this study, we propose a latent prosody model (LPM) aiming to jointly model the affections of tone and prosody state on F0. The main purposes are twofold including (1) automatic prosody state labeling and (2) improving tone recognition accuracy. The basic idea is to introduce latent prosody state variables into an additive statistic model of F0 which already considers the affecting factors of tone and speaker. Experiments on the Tree-Bank corpus showed that LPM not only gave meaningful prosody state labeling results but also improved the average tone recognition rate from 80.86% of a multi-layer perceptron (MLP) baseline to 82.55%.