MiniMax M3 428B — GB200 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB200 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.
At 50 tok/s/user on MiniMax M3 428B, GB200 NVL72 costs $0.29 per million tokens; MI300X costs $0.54. GB200 NVL72 is 87% more cost-efficient at this operating point.
GB200 NVL72 edges MI300X at 83 tok/s/user on MiniMax M3 428B — $0.73 per million tokens versus $1.32, a 82% cost-per-token gap.
Push MiniMax M3 428B to 116 tok/s/user and GB200 NVL72 lands at $2.27 per million tokens against MI300X's $1.88 — MI300X pulls ahead by 21%. (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.)
Chip pricing (owning hyperscaler): GB200 NVL72 $1.86/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 | GB200 NVL72:$0.287MI300X:$0.536 | GB200 NVL72:$0.725MI300X:$1.321 | GB200 NVL72:$2.275MI300X:$1.882 |
| Concurrency | GB200 NVL72:~217MI300X:~42 | GB200 NVL72:~83MI300X:~10 | GB200 NVL72:~20MI300X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.