What is Context Window?
A context window is the maximum amount of text (measured in tokens) a language model can consider at once — both the prompt you send and the response it generates. Larger windows let a model reason over more documents or longer conversations in a single call.
The context window bounds how much information an LLM can "see" per request. It shapes architecture decisions: whether you can pass whole documents inline or must retrieve and chunk them (RAG), and how much conversation history an assistant can remember before it needs summarising.