MiniMax M3 428B — GB300 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) 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: $0.56 per million tokens. H100: $0.40. Both at 47 tok/s/user on MiniMax M3 428B, with H100 39% cheaper.
Around the middle of the 15–142 tok/s/user interactivity band — at 79 tok/s/user — GB300 NVL72 runs $1.69 per million tokens on MiniMax M3 428B while H100 runs $0.71. H100 is the cheaper choice by 136%.
On MiniMax M3 428B at 110 tok/s/user, the per-million math comes out to $3.90 for GB300 NVL72 and $1.17 for H100; H100 delivers 233% more output per dollar. (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:$0.556H100:$0.401 | GB300 NVL72:$1.686H100:$0.714 | GB300 NVL72:$3.895H100:$1.170 |
| Concurrency | GB300 NVL72:~150H100:~86 | GB300 NVL72:~18H100:~28 | GB300 NVL72:~5H100:~12 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.