Head to head

o4-mini vs Kimi K2.6

On a blended workload of one million input tokens and three million output tokens, o4-mini is 1.0× cheaper than Kimi K2.6.

o4-miniKimi K2.6
Provider OpenAI Together AI
Input / MTok $1.1 $1.2
Output / MTok $4.4 $4.5
Cache read / MTok $0.275
Context window 200,000 262,144
Blended 1M in + 3M out $14.30 $14.70
Status ga ga

o4-mini detail   Kimi K2.6 detail