Context Window

Models and Architectures

The amount of text an AI model can consider at one time - its working memory for a conversation or document.

The context window is how much text a model can hold in mind at once, measured in tokens. Everything you have said in the conversation, plus documents you paste in, must fit inside it.When a chat gets longer than the window, the oldest parts fall out and the model genuinely forgets them. Newer models have very large windows, entire books can fit, but bigger windows also cost more to run.