Context windows
What takes up space in a context window?
The window holds the system prompt, the conversation so far, any documents you paste in, and the response the model writes. Every turn adds to it, so usage grows as a chat continues.
Several kinds of text share the same window. There is the system prompt, the standing instructions that set the model’s behavior. There is the conversation history, every earlier user message and model reply. There are any documents you add, such as a pasted report or an attached file. And there is the model’s own response, which counts too. Anthropic’s documentation states plainly that the window includes “the response itself.”[1]
Usage grows turn by turn. The same documentation describes “progressive token accumulation,” where “as the conversation advances through turns, each user message and assistant response accumulates within the context window,” and notes that “context usage grows linearly with each turn, with previous turns preserved completely.”[1] A long chat or a big pasted document can fill the window even when no single message is large. Each turn’s input is all the prior history plus the new message, and that turn’s output then becomes part of the next turn’s input.[1]
How much fits depends on the model. Window sizes have grown from tens of thousands of tokens to a million or more.
Stated context window sizes
- Anthropic Claude ↗
200K tokens on most models; 1M tokens on several current models including Opus 4.8 and Fable 5
References
- Context windows (Claude API docs) — Anthropic