Skip to content
The Internet Compass

AI

Context Window

The context window is the maximum quantity of text, measured in tokens, that a language model can process in one request, including the prompt, any retrieved documents, conversation history and the generated response.

Larger windows reduce the need for retrieval infrastructure but increase cost and latency, since the model processes everything supplied.

Models also exhibit uneven attention across long contexts, so filling a large window is not equivalent to the model using all of it well.