alt Hacker NewsWhere do you run sonnet/opus where you are limited to 128k, given they are both 1M context window models?
Replies
simonw • today at 7:11 PM
It's the output token limit, which has been 128,000 for Claude models for quite a while note
➕ show 1 reply
Where do you run sonnet/opus where you are limited to 128k, given they are both 1M context window models?
It's the output token limit, which has been 128,000 for Claude models for quite a while note
That's max output tokens per response limit, separate from context length