The maximum number of tokens (text, and in multimodal models also image/audio/video) a model can consider simultaneously as input in a single request, including the prompt, conversation history, and any attached documents.
In GENAI-L (Domain 1) it is one of the key criteria for choosing a foundation model: a large context window allows processing entire lengthy documents without needing to split them (chunking) or relying as heavily on RAG.
Context window is a concept that can show up on the exam. Check the full guide to see it in context.