The context window is the maximum amount of text — measured in tokens — that a language model can process in a single interaction, including both the input and the generated output.
Everything the model can "see" at once is limited to its context window. If a conversation or document exceeds this limit, earlier content falls outside the window and the model can no longer reference it.
Context window size varies by model. Larger context windows allow longer documents or conversations to be processed at once, but do not eliminate other model limitations such as hallucination.