By the Variask team · Updated
Definition
A context window is the amount of text an AI model can take in at once, including the question, the conversation so far and any documents or search results added to it, measured in tokens.
Everything the model uses to write an answer has to fit in its context window. When an engine searches the web, it can only pass a limited number of passages into that window, so it chooses the most relevant ones. Long, unfocused pages compete poorly for that space.
Questions
They have grown fast, from a few thousand tokens to hundreds of thousands or more in current models. Engines still choose what to include to keep answers fast and focused.
Related terms
How AI search works
Tokenization
Tokenization is how an AI model splits text into small pieces called tokens, often parts of words, before it reads or writes. Limits, costs and context windows are all measured in tokens.
ReadHow AI search works
Content chunking
Content chunking is the splitting of a page into smaller passages, so an AI system can store, find and quote the most relevant part instead of the whole page.
ReadHow AI search works
Large language model (LLM)
A large language model (LLM) is an AI model trained on very large amounts of text to understand and write language. LLMs power assistants such as ChatGPT, Gemini, Claude, Grok and DeepSeek.
ReadHow AI search works
Retrieval-augmented generation (RAG)
Retrieval-augmented generation (RAG) is a way of building AI answers where the system first retrieves relevant documents or web pages, then has the language model write the answer using them.
Read