SESKStuff Everyone Should Know
SESK: Stuff Everyone Should Know · sesk.info/ai-context-window-definition

What does an LLM's context window measure?

How many tokens the model can process in one prompt.

Start playing free

  1. How many facts it remembers forever
  2. How many users can chat at once
  3. How many tokens it can process at once ✔

Why: The context window is a token budget for a single request: your prompt, any documents and the conversation so far. Anything outside it simply is not seen by the model for that answer.

Huh, didn't know that: GPT-3, released in 2020, had a context window of 2048 tokens.

The dad joke
My short-term memory has a context window too. It closes right after someone tells me their name.
Like this card?
Play the game

References

Answer: How many tokens it can process at once. The context window is a token budget for a single request: your prompt, any documents and the conversation so far. Anything outside it simply is not seen by the model for that answer.

  1. Google Machine Learning Glossary: context window developers.google.com/machine-learning/glossary
    The number of tokens a model can process in a given prompt.
    Checked 2026-10-10.
  2. Brown et al., Language Models are Few-Shot Learners (arXiv 2005.14165) arxiv.org/pdf/2005.14165
    All models use a context window of nctx = 2048 tokens.
    Checked 2026-10-10.

Think this answer is wrong? Tap "Challenge this answer" on the card in the game and tell us why.

Test yourself in the game

Artificial IntelligenceWhat does a learned embedding assign to each input token?Artificial IntelligenceWhich statement correctly distinguishes model parameters from tokens?Artificial IntelligenceWhy is one written word not always one language-model token?

That's stuff everyone should know.