Context Window

How much text an AI can "see" at once — measured in tokens. Currently 100k-2M for frontier models.

Definition

The context window is the maximum input length the model can process. GPT-4o: 128k tokens. Claude 4 Opus: 1M tokens. Gemini 2: 2M tokens. Affects what kinds of long-document tasks are feasible.

Examples

  • 1M-token window can read an entire book
  • 128k-token window can read a long PDF

Related terms

Looking for actual gigs that use Context Window? Browse all live listings or filter by $100+/hr.