Head to head

LFM2.5 8B-A1B vs GPT-OSS 20B

On a blended workload of one million input tokens and three million output tokens, LFM2.5 8B-A1B is 1.7× cheaper than GPT-OSS 20B.

LFM2.5 8B-A1BGPT-OSS 20B
Provider Together AI Together AI
Input / MTok $0.03 $0.05
Output / MTok $0.12 $0.2
Cache read / MTok
Context window 32,768 128,000
Blended 1M in + 3M out $0.39 $0.65
Status ga ga

LFM2.5 8B-A1B detail   GPT-OSS 20B detail