In today’s automotive sector, a pressing need exists for accessible tools to predict and mitigate future CO2 emissions. However, existing solutions often lack transparency and comprehensibility. The goal of this initiative is to address the existing gap through the development of a cutting-edge modeling solution that integrates various car attributes to accurately estimate CO2 emissions. Motivated by the desire to empower vehicle manufacturers and consumers with actionable insights, our initiative employs explainable Artificial Intelligence (XAI) techniques to deliver predictions and interpret them transparently. Through this approach, we seek to foster informed decision- making and encourage the adoption of eco-friendly vehicles. Our proposed approach utilizes diverse car attributes to inform CO2 emission predictions, foster informed decision-making and encouraging the adoption of eco- friendly vehicles. Through the integration of XAI, our system ensures that stakeholders can understand and trust the predictions made by the model. The effectiveness of our approach through various graphs generated using SHAP (SHapley Additive exPlanations) and eli5 libraries. We interpret the models built with different algorithms carrying Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and XGBoost (XGB), demonstrating their predictive capabilities and providing insights into the factors influencing CO2 emissions. By employing interpretable AI techniques, we aim to drive sustainable practices within the automotive industry while ensuring the authenticity and distinctiveness of our contribution.