What Is a Context Window?

A context window is the amount of text an AI model can consider at one time, measured in tokens. It covers everything the model reads for a single response, including the prompt, any provided data, and the conversation so far. Anything beyond the window is not seen.

How a context window works

Everything sent to a model for one response has to fit inside its context window, and text is measured in tokens, which are chunks of words. When a conversation or document exceeds the window, something has to be dropped or summarized, because the model cannot see past the limit. Larger context windows let a model take in more at once, such as a long document or a lengthy conversation, without losing the earlier parts.

Why the context window matters

The context window matters because it sets a hard ceiling on how much a model can work with at a time. Exceed it and the model loses the earliest information, which can make it forget instructions given at the start of a long conversation or miss parts of a long document. It is also a cost factor, since more tokens in the window usually means more to process. Managing what goes in the window is the job of context engineering.