context window
The maximum amount of text a model can read at once before answering.
Language models read text in small chunks called tokens, roughly pieces of words. Every model has a limit on how many tokens it can take in for one answer. That limit is its context window. Text beyond it is simply invisible to the model.
Think of it as
Like a window that only shows part of a long document — pages beyond the frame are simply out of view.
Example
A model with a small context window cannot read a 300-page contract in one go. The team has to split it into parts, and the model may miss a clause in part one that changes the meaning of part three.