What is Context window?

A context window is the maximum amount of text an AI model can consider at once — your prompt plus its reply — measured in tokens.

Everything in play during a request shares one budget: your instructions, any documents you paste, the running conversation, and the model's own answer. When the total exceeds the window, the oldest material drops out of view — which is why a model can seem to "forget" the start of a long chat or a large document you pasted earlier.

Bigger windows let you work with more at once — whole reports, long transcripts, large codebases — but they aren't free: more tokens mean higher cost and sometimes weaker focus on the part that matters. Tight, well-structured prompts get more out of any window than dumping everything in and hoping the model finds the relevant bit.