Term · Intermediate

Context Window

The amount of text an AI model can consider at once, measured in tokens.

The context window is the maximum amount of text, prompt plus response, a language model can work with at once, counted in tokens (roughly three quarters of a word each). Current models handle from about 128,000 to over a million tokens. Go past the limit and the tool either refuses or trims older material, and even within it, details buried in very long inputs get less attention.

Also called context length, token limit, context, tokens

Related

More in Editing & Post