Conventional methods face limitations when it comes to producing near-net-shape products of high-strength advanced engineering alloys, while additive manufacturing as an alternative approach have garnered the interest of artisans and researchers. High-performance engineering materials, such as nickel-based superalloys, are specifically formulated to endure harsh conditions like elevated temperatures, extended exposure time, and corrosive surroundings. Consequently, there is a significant demand to study the high temperatures mechanical characteristics of advanced high-strength alloys produced through additive manufacturing. In this research, the high temperature flow behavior of Inconel625 superalloy produced through selective laser melting has been investigated. For this purpose, hot compression tests were performed at temperatures of 800, 900, 1000, and 1100 ℃ under the strain rates of 0.001, 0.01, and 0.1s-1. In order to modeling the flow stress behavior, modified Arrhenius-type model and artificial neural network model were employed. Standard statistical parameters in the form of correlation coefficient (R), root mean square error (RMSE) and average absolute relative error (AARE) were used to evaluate the accuracy of the developed models. Due to the significant changes in the strain rate sensitivity and deformation activation energy in the studied temperature range, Arrhenius model could not accurately predict the high temperature flow behavior. While the artificial neural network model represented high capability in modeling the hardening and softening behavior of the investigated superalloy. Based on the predicted data, power efficiency and dissipation maps were constructed at strains of 0.1, 0.2, 0.3, and 0.4, then the metallurgical instability regions and optimal deformation conditions were identified.