Head to head

Magistral Medium vs Kimi K2.6

On a blended workload of one million input tokens and three million output tokens, Kimi K2.6 is 1.2× cheaper than Magistral Medium.

Magistral MediumKimi K2.6
Provider Mistral Together AI
Input / MTok $2 $1.2
Output / MTok $5 $4.5
Cache read / MTok
Context window 262,144
Blended 1M in + 3M out $17.00 $14.70
Status ga ga

Magistral Medium detail   Kimi K2.6 detail