What is a model's "context window"?

Question

Accepted Answer

The maximum amount of text — measured in tokens — it can consider at once — The context window is how much text (in tokens) a model can attend to at once. It's not about users, reply size alone, or disk — it's the total working span for one request.

Answer

The maximum number of users — it can serve at the same moment in parallel

Answer

The maximum size of a reply — the longest answer it is allowed to produce

Answer

The maximum file it can open — the largest document it can store on a disk

What is a model's "context window"?

Why this is the answer

More AI & LLM Fundamentals flashcards