Head to head

Llama Prompt Guard 2 86M vs LFM2.5 8B-A1B

On a blended workload of one million input tokens and three million output tokens, Llama Prompt Guard 2 86M is 2.4× cheaper than LFM2.5 8B-A1B.

Llama Prompt Guard 2 86MLFM2.5 8B-A1B
Provider Groq Together AI
Input / MTok $0.04 $0.03
Output / MTok $0.04 $0.12
Cache read / MTok
Context window 32,768
Blended 1M in + 3M out $0.16 $0.39
Status preview ga

Llama Prompt Guard 2 86M detail   LFM2.5 8B-A1B detail