APEX AI is a full-stack, multi-model hybrid chatbot assistant designed to deliver intelligent conversationalcapabilities in both online and offline environments. Built on a FastAPI backend and a single-page responsivefrontend, the system integrates four large language models — Groq Llama 3.3 70B, Google Gemini Flash 1.5,Ollama Phi-3, and Ollama TinyLlama — providing seamless automatic switching between cloud-based andlocally hosted inference engines depending on internet availability. The platform supports multimodal inputsincluding text, images (via Gemini vision), and file uploads, real-time DuckDuckGo web search, and browsernative voice input. Session state is managed entirely in-memory using Python dictionaries, ensuring zero-databaseoverhead and rapid deployment. Experimental evaluation confirms sub-500 ms latency for online models andgraceful offline degradation without user-visible interruption, making APEX AI a practical solution forconnectivity-constrained environments.