Remember: K2 is *not* a reasoning model. And very few active tokens in the MoE. So it's using less tokens, *and* each token is cheaper and faster.
K2 Model: Efficient Token Usage Without Reasoning
By
–
By
–
Remember: K2 is *not* a reasoning model. And very few active tokens in the MoE. So it's using less tokens, *and* each token is cheaper and faster.