What is Context window?
Also called: context length · context limit
The context window is the maximum amount of text (measured in tokens) a model can consider at once — your prompt, the conversation so far, and its own answer.
Every model has a limit on how much it can "see" at one time. Everything counts against it: the system prompt, every earlier message, the documents you pasted, and the answer being written. Modern models handle anywhere from tens of thousands to over a million tokens, but the limit is real — once you exceed it, the oldest content is dropped or the request fails.
Bigger isn't automatically better: models attend less reliably to the middle of very long inputs, and long prompts cost more and run slower. The practical rule is to include what changes the answer and cut what doesn't.
- Put the most important instructions at the start and the end of a long prompt.
- Summarise long earlier turns instead of re-pasting them.
- For big documents, paste the relevant sections, not the whole file.
Use it right now
Ask our brain anything on the homepage — it remembers the whole conversation — or write a brief in the Studio and see the prompt it compiles to.