Word of the Day
Context Window
The context window is the maximum amount of text (in tokens) a model can consider at once — prompt plus its answer.
Get it freeThe context window is the model's working memory for a single request: everything you paste in, the system prompt, the conversation history, and the answer it generates all have to fit within it, measured in tokens. Exceed it and the oldest content is dropped or the request is rejected.
Bigger windows let you paste long documents, transcripts, or codebases and ask questions across all of them. But models can still lose track of details buried in the middle of very long inputs, so structure and the placement of key instructions still matter.
Related: token · rag · few shot prompting · system prompt
One of these every weekday
Three minutes. One prompt, one word, one skill. You're now better at AI than you were yesterday.
Free. All terms