Head to head
MiniMax M2.7 vs Inkling Small
On a blended workload of one million input tokens and three million output tokens, MiniMax M2.7 is 1.1× cheaper than Inkling Small.
| MiniMax M2.7 | Inkling Small | |
|---|---|---|
| Provider | Fireworks AI | Together AI |
| Input / MTok | $0.3 | $0.5 |
| Output / MTok | $1.2 | $1.2 |
| Cache read / MTok | $0.06 | — |
| Context window | — | 524,288 |
| Blended 1M in + 3M out | $3.90 | $4.10 |
| Status | ga | ga |