Head to head

MiniMax M2.7 vs Llama 3.3 70B Instruct Turbo

On a blended workload of one million input tokens and three million output tokens, MiniMax M2.7 is 1.1× cheaper than Llama 3.3 70B Instruct Turbo.

MiniMax M2.7Llama 3.3 70B Instruct Turbo
Provider Fireworks AI Together AI
Input / MTok $0.3 $1.04
Output / MTok $1.2 $1.04
Cache read / MTok $0.06
Context window 131,072
Blended 1M in + 3M out $3.90 $4.16
Status ga ga

MiniMax M2.7 detail   Llama 3.3 70B Instruct Turbo detail