Head to head
DeepSeek V4 Pro vs MiniMax M3
On a blended workload of one million input tokens and three million output tokens, DeepSeek V4 Pro is 1.3× cheaper than MiniMax M3.
| DeepSeek V4 Pro | MiniMax M3 | |
|---|---|---|
| Provider | DeepSeek | Together AI |
| Input / MTok | $0.435 | $0.3 |
| Output / MTok | $0.87 | $1.2 |
| Cache read / MTok | $0.003625 | — |
| Context window | 1,000,000 | 524,288 |
| Blended 1M in + 3M out | $3.04 | $3.90 |
| Status | ga | ga |