← Back to context Comment by dyauspitr 9 hours ago Then what is Astra high-extra high-Ultra? That’s effort within each tier? 2 comments dyauspitr Reply Readerium 8 hours ago Yes that is number of reasoning tokens used.Performance increases both with larger model (Luna vs Sol)And with more reasoning (low vs xhigh) MaKey 8 hours ago Exactly
Readerium 8 hours ago Yes that is number of reasoning tokens used.Performance increases both with larger model (Luna vs Sol)And with more reasoning (low vs xhigh)
Yes that is number of reasoning tokens used.
Performance increases both with larger model (Luna vs Sol)
And with more reasoning (low vs xhigh)
Exactly