Head to head
MiniMax M3 vs Gemma 4 31B IT
On a blended workload of one million input tokens and three million output tokens, Gemma 4 31B IT is 1.2× cheaper than MiniMax M3.
| MiniMax M3 | Gemma 4 31B IT | |
|---|---|---|
| Provider | Together AI | Together AI |
| Input / MTok | $0.3 | $0.39 |
| Output / MTok | $1.2 | $0.97 |
| Cache read / MTok | — | — |
| Context window | 524,288 | 262,144 |
| Blended 1M in + 3M out | $3.90 | $3.30 |
| Status | ga | ga |