Browse all
context window
876
#1·3h ago
The maximum amount of text an LLM can "see" at once, measured in tokens. Longer windows let models process whole codebases or novels in a single request.
"Claude Opus 4.7 has a 1M-token context window — you can dump a whole repo in."
Comments (0)
No comments yet — say something.
Have a better definition?
Add your own interpretation of "context window".