What is Context Window?
The context window is the maximum amount of text, measured in tokens, an AI model can consider at one time.
The context window is the model's working memory: everything it can see while producing an answer, including the system instructions, your prompt, uploaded documents, and the conversation so far. Modern models range from tens of thousands of tokens to a million or more, which is the difference between a long email and an entire contract set. When you exceed the window, older content is dropped or summarised, which is why long chats start forgetting details you gave at the beginning. Bigger is not automatically better. Filling a huge window costs more per request, can slow responses, and models often pay less attention to material buried in the middle of very long inputs. In practice, a well-designed retrieval system that feeds a model the ten most relevant pages usually beats dumping five hundred pages into a giant window. When comparing tools, check the effective limit on your plan — the underlying model may support more than the product actually allows.
Also known as
- context length
- token limit
Related tools
- Claude — Thoughtful, safety-focused AI assistant with excellent reasoning.
- Google Gemini — Google's multimodal AI with real-time information access.
- ChatGPT — The most versatile AI assistant for writing, research, and brainstorming.
- Perplexity AI — AI search engine that gives direct answers with cited sources.
- Cursor — AI-first code editor that understands your entire project.
Related terms
- Token (AI) — A token is the small chunk of text — roughly three-quarters of a word — that AI models read and generate, and that most AI pricing is based on.
- Large Language Model (LLM) — An LLM is an AI model trained on huge amounts of text that predicts language well enough to write, summarise, translate, and answer questions.
- RAG (Retrieval-Augmented Generation) — RAG is a technique where an AI tool searches your documents first, then writes an answer grounded in what it found.
- Prompt Engineering — Prompt engineering is the practice of writing instructions that reliably get the output you want from an AI tool.
Category: AI Concepts