Accurate pressure drop prediction in multiphase flow for horizontal and near horizontal pipes is essential for optimal flow line and piping network design. Since 1950, several correlations and mechanistic models have been developed. In addition to their applicability constraints, all known correlations fail to deliver the requisite precision of pressure drop predictions. In comparison to empirical correlations, the recently established mechanistic models improved pressure drop prediction. However, there is still a need to enhance prediction accuracy in order to design and build surface piping networks and wells that are more reliable and cost-effective. In this research, a model for predicting pressure drop in horizontal and near-horizontal pipelines has been developed using Adaptive Neuro Fuzzy Inference System (ANFIS) as an approach, offering a greater precision and simplicity. The ANFIS approach allows the fuzzy modeling procedure to learn information about a data set in order to compute the membership function parameters that best allow the associated fuzzy inference system to trace the input/output data. Field data covering a wide range of variables were used to develop and test the model. A total number of 450 field data sets, gathered from the Asian region, were used in the model development. A total of 337 data sets were used for training and 113 data sets were used for testing. Prior to the completion of the model in the development phase, trend analysis was performed. This is to verify that the model is stable and to confirm whether or not the produced model is physically valid and simulates the actual physical process. Following that, a statistical analysis was performed to establish the percentage of error of the predicted value versus the actual measured data. In addition, to compare the performance of the new ANFIS model to previous empirical correlations and mechanistic models, graphical and statistical approaches were used. The new model generated extraordinarily accurate pressure drop predictions, outperforming known correlations and the most recent mechanistic models by a wide margin.