Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

context window

The fixed maximum number of tokens a model can attend over at once, covering both the prompt and the model's own output so far.

A model's context window is the fixed maximum number of token positions it can process in a single forward pass. Every token in the prompt and every token the model has generated so far in the current response counts against this limit.

Examples

  • A model with an 8,000-token context window can't process a prompt plus response totaling more than 8,000 tokens -- the excess simply doesn't fit.

See also

token KV cache
Read the full section →
Graph settings

Calculator