Head to head
Ministral 3 8B vs LFM2.5 8B-A1B
On a blended workload of one million input tokens and three million output tokens, LFM2.5 8B-A1B is 1.5× cheaper than Ministral 3 8B.
| Ministral 3 8B | LFM2.5 8B-A1B | |
|---|---|---|
| Provider | Mistral | Together AI |
| Input / MTok | $0.15 | $0.03 |
| Output / MTok | $0.15 | $0.12 |
| Cache read / MTok | — | — |
| Context window | — | 32,768 |
| Blended 1M in + 3M out | $0.60 | $0.39 |
| Status | ga | ga |