Context Window

A context window is the maximum amount of text (measured in tokens) that an AI model can process in a single request. It includes both the input (your message plus conversation history) and the output (the model's response).

How It Works

Context window sizes vary dramatically between models. GPT supports 128K tokens. Claude supports 200K tokens. Some models support over 1 million tokens. A larger context window means the model can consider more information when generating a response, which is critical for long documents, complex codebases, and extended conversations. However, larger context windows typically cost more per request.

Context Window in Chapeta

Chapeta shows real-time prompt token counts from the API, so you can see exactly how much context you are using. When switching between models with different context sizes, the indicator adapts to the new model's limit. The context window is especially important when using file attachments, as documents and code files consume context tokens.

See Context Window in action with Chapeta