What is a context window in artificial intelligence?

The context window is not a browser window or the "context" of a marketing plan: it is everything a language model has in front of it at the moment of answering. It matters to a store from two sides. When an assistant answers about your products, it can only use what of your page made it into that window, next to what came from other stores. And when a tool writes your product pages with an LLM (large language model), what decides which data gets used is what that tool puts inside.

How it works

Anthropic defines it as all the text a model can reference while generating a response, including the response itself. It is not the enormous corpus the model was trained on, but a "working memory".⁠^{[1]Anthropic, Claude documentation. Context windows} Google uses almost the same image: a short-term memory, with a limited capacity to hold information before generating the answer.⁠^{[2]Google AI for Developers, Gemini API documentation (updated June 22, 2026). Long context}

It is measured in tokens, the pieces of text the model splits what it reads into, and the count includes much more than the question. In Claude's API it counts everything that goes in the request: system instructions, every message in the conversation including tool results, images and documents, tool definitions and, on top of that, what the model generates in that turn, reasoning included.⁠^{[1]Anthropic, Claude documentation. Context windows} OpenAI sums it up in one rule: the request and the response together cannot exceed the model's maximum context length.⁠^{[3]OpenAI, API documentation. Key concepts}

The size has grown a lot. As of October 2026, current Claude models have a one-million-token window and can generate up to 128,000 output tokens per request; other models in the same family stay at 200,000.⁠^{[1]Anthropic, Claude documentation. Context windows} Gemini also accepts a million tokens, and Google translates that into things you can picture: about 50,000 lines of code, eight average-length novels or the transcripts of more than 200 podcast episodes.⁠^{[2]Google AI for Developers, Gemini API documentation (updated June 22, 2026). Long context}

When something does not fit, what happens depends on who manages the window. In Claude's API, if the input alone already exceeds the window, the request is rejected with a prompt-too-long error. Chat interfaces, by contrast, can drop the oldest part of the conversation to make room for the new.⁠^{[1]Anthropic, Claude documentation. Context windows}

More context is not better

Anthropic itself warns about it on the same page: a bigger window allows longer tasks, but as the number of tokens grows, accuracy and recall degrade, a phenomenon it calls context rot.⁠^{[1]Anthropic, Claude documentation. Context windows} Google gives a figure for the same problem: finding a single fact in a long context works around 99% of the time, but accuracy drops noticeably when several facts have to be found at once in the same context.⁠^{[2]Google AI for Developers, Gemini API documentation (updated June 22, 2026). Long context}

Position counts too. A study by Nelson F. Liu and six other authors, published in 2023 in the journal TACL, had several models answer questions with many documents in front of them. Performance was best when the relevant information was at the beginning or the end of the context, and dropped significantly when it was in the middle, even in models built for long contexts.⁠^{[4]arXiv (Liu, Lin, Hewitt, Paranjape, Bevilacqua, Petroni and Liang; TACL 2023). Lost in the Middle: How Language Models Use Long Contexts} That is why Anthropic's engineers treat context as a finite resource with diminishing returns, and their advice is to look for the smallest set of useful information that makes the result you want likely.⁠^{[5]Anthropic, engineering blog (September 29, 2025). Effective context engineering for AI agents}

In a store

A fictional example: a tool has to write the description of a travel tripod. It can fill the window three ways:

The third option is the one that follows from this page's sources. Clione, for example, does not send the whole catalog: with each product travel the store's instructions, up to 10,000 characters, the merchant's answers about that product and, if the store turns it on, the four most relevant excerpts from its documents, about 1,200 tokens.

The same holds in reverse for the assistants that read your site: your product page shares a window with other stores' pages, and enters in pieces, not whole. A fact that only makes sense with the rest of the page around it has fewer chances of being useful.

How to check it

1. Look up the window and the output limit of the model your tool uses in the provider's documentation. They are two different figures, and both are measured in tokens.⁠^{[1]Anthropic, Claude documentation. Context windows}
2. Count the tokens of a typical request before sending it. Anthropic recommends its token counting precisely so you do not go over the window.⁠^{[1]Anthropic, Claude documentation. Context windows}
3. Take out what does not help. If the context carries the whole catalog to describe one product, trim it to what talks about that product.⁠^{[5]Anthropic, engineering blog (September 29, 2025). Effective context engineering for AI agents}
4. Put the key facts at the beginning or the end of what you give the model, not buried in the middle of a long document.⁠^{[4]arXiv (Liu, Lin, Hewitt, Paranjape, Bevilacqua, Petroni and Liang; TACL 2023). Lost in the Middle: How Language Models Use Long Contexts}
5. If an answer comes out cut off, look at the reason. In Claude's API, a generation that reaches the window limit stops with the reason model_context_window_exceeded.⁠^{[1]Anthropic, Claude documentation. Context windows}

Related concept: RAG

RAG (retrieval-augmented generation) and the context window are explained together. Google says that models with small windows needed to retrieve only what was relevant, summarize or trim messages, and that a large window allows another route: giving all the relevant information up front.⁠^{[2]Google AI for Developers, Gemini API documentation (updated June 22, 2026). Long context} But context rot and the position effect are still there,⁠^{[1]Anthropic, Claude documentation. Context windows}⁠^{[4]arXiv (Liu, Lin, Hewitt, Paranjape, Bevilacqua, Petroni and Liang; TACL 2023). Lost in the Middle: How Language Models Use Long Contexts} so retrieving well has not stopped being useful. RAG decides what goes in; the window is the space it goes into.

To keep going, the entry on tokens explains the unit the window is measured in, and the reading path orders the rest of the terms.