Context Window
The maximum amount of text (measured in tokens) an AI model can consider at once. Larger context windows allow the model to reference more information in a single conversation.
Why it matters
The context window is the AI's short-term memory for a conversation or document. It matters because everything you want the model to consider, your question, past messages, and any pasted text, has to fit inside it. When a long chat starts losing track of earlier details, or a giant file won't process, the context window is usually the reason. Bigger windows let you work with more at once.
In practice
Imagine explaining a project to someone who can only hold about 20 pages in mind at a time. Feed them page 100 and they may forget page 1. Modern models have much larger windows, some fit whole books, but the limit still exists. If an AI ignores an instruction you gave far earlier in a very long chat, restating it usually brings it back into view.
Related terms
Artificial Intelligence (AI)
The simulation of human intelligence by computer systems, including learning, reasoning, and self-correction. Modern AI is primarily powered by machine learning and neural networks.
Large Language Model (LLM)
An AI model trained on vast amounts of text data that can generate, summarize, translate, and analyze human language. Examples include GPT-4, Claude, Gemini, and Llama.
Natural Language Processing (NLP)
The branch of AI focused on enabling computers to understand, interpret, and generate human language. Powers chatbots, translation, sentiment analysis, and text summarization.
Prompt
The text instruction you give to an AI model to generate a response. Prompt quality directly impacts output quality — better prompts yield dramatically better results.
Token
The basic unit of text that AI models process — roughly 3/4 of a word in English. 'Unbelievable' is 3 tokens. Token limits determine how much text a model can process at once.
Tokenizer
The component that splits text into tokens (sub-word units) before feeding it to an AI model. Different models use different tokenizers — affecting how they count input length, handle multilingual text, and process code.