# Context window

URL: https://onlykin.ai/glossary/context-window
Updated: 2026-06-04
Category: Model behavior

## Definition

A context window is the maximum amount of text a language model can consider at once when generating a reply.

## Quick Answer

In AI roleplay, the context window contains the system prompt, character card, persona, summaries, and recent messages. When it fills up, older details must be dropped, summarized, or retrieved another way.

## Plain Language

The model does not remember everything by default. It can only respond from the information placed in front of it for the next turn.

## Why It Matters

Most complaints about characters forgetting names, promises, locations, or earlier scenes trace back to context-window limits and weak memory design.

## OnlyKin Angle

OnlyKin should explain context windows plainly so users understand why compact memory and structured cards matter.

## Related Terms

- Token: https://onlykin.ai/glossary/token
- Semantic memory: https://onlykin.ai/glossary/semantic-memory
- Lorebook: https://onlykin.ai/glossary/lorebook
- System prompt: https://onlykin.ai/glossary/system-prompt

## Sources

- [OpenAI Help: What are tokens?](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them) - Used for explaining tokens as the units models process and why input length matters.
- [OnlyKin guide to why AI characters forget](https://onlykin.ai/blog/why-ai-characters-forget-and-how-to-fix-it) - Used for roleplay-specific context-window examples.