Head to head

text-embedding-3-small vs LFM2.5 8B-A1B

On a blended workload of one million input tokens and three million output tokens, text-embedding-3-small is 19.5× cheaper than LFM2.5 8B-A1B.

text-embedding-3-smallLFM2.5 8B-A1B
Provider OpenAI Together AI
Input / MTok $0.02 $0.03
Output / MTok $0.12
Cache read / MTok
Context window 32,768
Blended 1M in + 3M out $0.02 $0.39
Status ga ga

text-embedding-3-small detail   LFM2.5 8B-A1B detail