Learn · AI fundamentals
A context window is the maximum amount of text an AI model can hold in mind at once, counted in tokens. It includes your prompt, any documents you attach, the conversation so far, and the answer being written. Once you exceed it, the model loses track of the earliest content.
Context windows have grown fast. As of July 2026, frontier models commonly offer around one million tokens, enough to hold a large codebase or a stack of long documents in a single request. A few push well beyond that.
A bigger window isn't automatically better. Models can still lose focus in the middle of very long inputs, and every extra token costs money and time. Giving the model the right context often beats giving it the most.
Updated July 2026
Related
Tokens are the chunks of text an AI model reads and writes. A token is roughly three-quarters of a word in English, so 1,000 tokens is about 750 words. They matter because AI pricing and limits are measured in tokens, not words or characters.
RAG (retrieval-augmented generation) feeds a model your data at question time, so it answers from your documents without changing the model. Fine-tuning retrains a model on your examples so it internalizes a style or task. RAG is for knowledge, fine-tuning is for behavior.
It depends on the job. As of July 2026 the main families are OpenAI's GPT-5 models, Anthropic's Claude models, and Google's Gemini models, each with a small, fast, cheap tier and a larger, more capable one. Match the tier to the task instead of always reaching for the most powerful.