This paper presents a deep learning-based API designed for automated brain tumour classification from MRI scans, addressing the need for accessible diagnostic tools in clinical and resource-limited environments. Leveraging two state-of-the-art models, YOLO for real-time object detection and Roboflow for multi-label image classification, the study develops and evaluates an AI-powered diagnostic API implemented with FastAPI. The models were trained on a publicly available dataset containing glioma, meningioma, pituitary tumours, and non-tumorous images. Evaluation metrics include accuracy, validation accuracy, and confusion matrices. Roboflow achieved superior classification accuracy (96.1%) compared to YOLO (84.72%), while YOLO demonstrated faster inference, making it ideal for real-time use. The API ensures ease of deployment, robust handling of low-quality inputs, and compatibility with various clinical setups. Ethical considerations such as data privacy and model transparency were also addressed. The study concludes that combining deep learning with accessible APIs can significantly enhance diagnostic support, but stresses the importance of explainability, regulatory compliance, and broader dataset diversity for full-scale clinical integration.