This thesis explores the use of IBM CPLEX optimization tools within the Python programming environment for solving Linear Programming (LP) problems. It focuses on comparing the CPLEX Python API and the Pyomo framework, analyzing their differences in performance, usability, and integration with Python. Through practical examples like a bakery production optimization problem, the study highlights the strengths of each approach. Additionally, the thesis examines sensitivity analysis, showcasing how changes in input parameters affect optimization outcomes. It also addresses handling MPS file formats, emphasizing the direct capabilities of the CPLEX API compared to the more manual approach required in Pyomo. The findings provide insights for researchers and practitioners seeking efficient optimization solutions