LearnHow LLMs WorkContext Windows
How LLMs Work

Context Windows

The budget your model runs on

The context window is the total number of tokens your model can process in one call — input + output combined. It's not just a limit, it's a budget: every token you spend on instructions is a token you can't spend on reasoning.

Why this matters

Context engineering — what goes in, what stays out — is the new prompt engineering. Teams that manage this well get 3-5x better results from the same model.