The context window determines how much information the model can keep in view at once, such as long documents or the conversation so far. When the limit is exceeded, older content is truncated and lost. A larger context window enables more complex tasks like analyzing entire books or codebases. Since all tokens in the window are processed, longer inputs also increase cost and latency.
Context Window
The context window is the maximum amount of text (measured in tokens) an AI model can process at once, including input and output. Modern models range from a few thousand to several million tokens.