Basics
Context window
The maximum number of tokens a model can consider at once, counting both your input and its output.
A 200k context fits a long report; 1M tokens fits several books or a large codebase. Some providers charge more above a threshold, for example above 200k or 272k tokens, so a long prompt can cost more per token.
Frequently asked questions
What does Context window mean?
The maximum number of tokens a model can consider at once, counting both your input and its output. A 200k context fits a long report; 1M tokens fits several books or a large codebase. Some providers charge more above a threshold, for example above 200k or 272k tokens, so a long prompt can cost more per token.