Head to head

Ministral 3 3B vs LFM2.5 8B-A1B

On a blended workload of one million input tokens and three million output tokens, LFM2.5 8B-A1B is 1.0× cheaper than Ministral 3 3B.

Ministral 3 3BLFM2.5 8B-A1B
Provider Mistral Together AI
Input / MTok $0.1 $0.03
Output / MTok $0.1 $0.12
Cache read / MTok
Context window 32,768
Blended 1M in + 3M out $0.40 $0.39
Status ga ga

Ministral 3 3B detail   LFM2.5 8B-A1B detail