MiniMax M3 428B — GB200 NVL72 vs H100 Performance per Dollar
Cost per million tokens of GB200 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.
Push MiniMax M3 428B to 52 tok/s/user and GB200 NVL72 lands at $0.32 per million tokens against H100's $0.39 — GB200 NVL72 pulls ahead by 20%.
GB200 NVL72: $0.81 per million tokens. H100: $0.75. Both at 87 tok/s/user on MiniMax M3 428B, with H100 9% cheaper.
Toward the upper edge of the 17–157 tok/s/user interactivity band — at 122 tok/s/user — GB200 NVL72 runs $2.45 per million tokens on MiniMax M3 428B while H100 runs $1.20. H100 is the cheaper choice by 104%. (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 · H100 $1.17/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:$0.323H100:$0.389 | GB200 NVL72:$0.809H100:$0.745 | GB200 NVL72:$2.449H100:$1.199 |
| Concurrency | GB200 NVL72:~180H100:~72 | GB200 NVL72:~74H100:~22 | GB200 NVL72:~18H100:~10 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.