MiniMax M2.5/M2.7 — GB200 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) on MiniMax M2.5/M2.7. 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.
GB200 NVL72 edges MI300X at 44 tok/s/user on MiniMax M2.5/M2.7 — $0.11 per million tokens versus $0.25, a 138% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 61 tok/s/user and GB200 NVL72 lands at $0.19 per million tokens against MI300X's $0.40 — GB200 NVL72 pulls ahead by 111%.
GB200 NVL72: $0.48 per million tokens. MI300X: $0.75. Both at 78 tok/s/user on MiniMax M2.5/M2.7, with GB200 NVL72 55% cheaper. (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 · MI300X $1.12/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:$0.105MI300X:$0.250 | GB200 NVL72:$0.191MI300X:$0.402 | GB200 NVL72:$0.480MI300X:$0.747 |
| Concurrency | GB200 NVL72:~1012MI300X:~63 | GB200 NVL72:~296MI300X:~26 | GB200 NVL72:~64MI300X:~11 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.