MiniMax M3 428B — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on MiniMax M3 428B. Owning-hyperscaler TCO normalized by output tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
On MiniMax M3 428B at 93 tok/s/user, the per-million math comes out to $0.05 for GB300 NVL72 and $0.11 for MI355X; GB300 NVL72 delivers 102% more output per dollar.
At 164 tok/s/user on MiniMax M3 428B, GB300 NVL72 costs $0.26 per million tokens; MI355X costs $0.20. MI355X is 34% more cost-efficient at this operating point.
MI355X edges GB300 NVL72 at 236 tok/s/user on MiniMax M3 428B — $0.33 per million tokens versus $0.36, a 11% cost-per-token gap. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB300 NVL72:$0.052MI355X:$0.106 | GB300 NVL72:$0.264MI355X:$0.197 | GB300 NVL72:$0.363MI355X:$0.327 |
| Concurrency | GB300 NVL72:~672MI355X:~22 | GB300 NVL72:~20MI355X:~7 | GB300 NVL72:~8MI355X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.