What Is Context Window?

Context Window — the maximum amount of text, measured in tokens, that a large language model can take into account at once — including both the input prompt and the generated output.

The context window sets how much information a model can "see" in a single interaction. It matters for governance because anything outside it is effectively forgotten, and because long windows often hold sensitive or proprietary data, making retention and leakage relevant risks. Larger windows reduce but do not remove the need for retrieval and grounding.

Source: Machine-learning literature