Context Window

The maximum amount of text (measured in tokens) that an AI model can process in a single conversation or request.

The context window is the model’s working memory. It determines how much text — including your conversation history, system prompt, and the model’s replies — can fit in a single interaction.

Why It Matters

A larger context window means the model can reference more of your conversation without “forgetting” earlier messages. This is critical for long documents, multi-turn chats, and complex tasks.

Typical Sizes

GPT-4o — 128K tokens (~96,000 words)
Claude Sonnet — 200K tokens (~150,000 words)
Gemini Pro — 1M+ tokens

Tips

Keep system prompts concise to leave more room for conversation
Summarize earlier context if you’re hitting limits
Use models with larger windows for document-heavy tasks