MiniMax M3 428B — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 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.
Push MiniMax M3 428B to 52 tok/s/user and GB200 NVL72 lands at $0.38 per million tokens against MI355X's $0.15 — MI355X pulls ahead by 157%.
GB200 NVL72: $1.00 per million tokens. MI355X: $0.25. Both at 87 tok/s/user on MiniMax M3 428B, with MI355X 296% cheaper.
Toward the upper edge of the 17–157 tok/s/user interactivity band — at 122 tok/s/user — GB200 NVL72 runs $2.86 per million tokens on MiniMax M3 428B while MI355X runs $0.39. MI355X is the cheaper choice by 633%. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/GPU/hr · MI355X $1.48/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB200 NVL72:$0.382MI355X:$0.149 | GB200 NVL72:$0.996MI355X:$0.251 | GB200 NVL72:$2.862MI355X:$0.391 |
| Concurrency | GB200 NVL72:~180MI355X:~112 | GB200 NVL72:~74MI355X:~41 | GB200 NVL72:~18MI355X:~19 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.