MiniMax M2.5/M2.7 — GB300 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) 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.
At 59 tok/s/user on MiniMax M2.5/M2.7, GB300 NVL72 costs $0.19 per million tokens; H100 costs $0.58. GB300 NVL72 is 207% more cost-efficient at this operating point.
GB300 NVL72 edges H100 at 78 tok/s/user on MiniMax M2.5/M2.7 — $0.48 per million tokens versus $0.94, a 96% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 98 tok/s/user and GB300 NVL72 lands at $0.84 per million tokens against H100's $1.72 — GB300 NVL72 pulls ahead by 103%. (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 · H100 $1.30/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:$0.187H100:$0.576 | GB300 NVL72:$0.479H100:$0.936 | GB300 NVL72:$0.845H100:$1.717 |
| Concurrency | GB300 NVL72:~405H100:~43 | GB300 NVL72:~64H100:~12 | GB300 NVL72:~32H100:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.