MiniMax M2.5/M2.7 — GB300 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI325X (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.
On MiniMax M2.5/M2.7 at 46 tok/s/user, the per-million math comes out to $0.13 for GB300 NVL72 and $0.22 for MI325X; GB300 NVL72 delivers 68% more output per dollar.
At 65 tok/s/user on MiniMax M2.5/M2.7, GB300 NVL72 costs $0.25 per million tokens; MI325X costs $0.48. GB300 NVL72 is 91% more cost-efficient at this operating point.
GB300 NVL72 edges MI325X at 85 tok/s/user on MiniMax M2.5/M2.7 — $0.58 per million tokens versus $1.09, a 88% cost-per-token gap. (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): GB300 NVL72 $2.65/GPU/hr · MI325X $1.28/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 | GB300 NVL72:$0.129MI325X:$0.217 | GB300 NVL72:$0.251MI325X:$0.479 | GB300 NVL72:$0.582MI325X:$1.094 |
| Concurrency | GB300 NVL72:~593MI325X:~147 | GB300 NVL72:~128MI325X:~38 | GB300 NVL72:~64MI325X:~16 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.