MiniMax M3 428B — GB300 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) 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.
GB300 NVL72: $0.04 per million tokens. MI300X: $0.40. Both at 56 tok/s/user on MiniMax M3 428B, with GB300 NVL72 911% cheaper.
Around the middle of the 22–162 tok/s/user interactivity band — at 92 tok/s/user — GB300 NVL72 runs $0.05 per million tokens on MiniMax M3 428B while MI300X runs $0.50. GB300 NVL72 is the cheaper choice by 881%.
On MiniMax M3 428B at 127 tok/s/user, the per-million math comes out to $0.16 for GB300 NVL72 and $0.76 for MI300X; GB300 NVL72 delivers 388% more output per dollar. (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 · MI300X $0.95/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:$0.039MI300X:$0.397 | GB300 NVL72:$0.051MI300X:$0.501 | GB300 NVL72:$0.156MI300X:$0.761 |
| Concurrency | GB300 NVL72:~2048MI300X:~15 | GB300 NVL72:~776MI300X:~6 | GB300 NVL72:~57MI300X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.