Context Window

What it is

The context window is the maximum amount of text (measured in tokens) that a model can consider at once. It includes both your input and the model's output. Early GPT models had 4,000 tokens; modern models can handle 100,000 to 1 million or more. Older parts of a conversation are dropped when the limit is reached.

Why it matters

The context window determines how much information you can provide and how long conversations can be before the model "forgets" earlier content. Larger context windows enable working with longer documents and maintaining longer conversations, but don't assume infinite memory—there are still practical limits.