MiniMax M3 428B — GB200 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H200 (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.
GB200 NVL72: $0.38 per million tokens. H200: $0.39. Both at 52 tok/s/user on MiniMax M3 428B, with GB200 NVL72 3% cheaper.
Around the middle of the 17–157 tok/s/user interactivity band — at 87 tok/s/user — GB200 NVL72 runs $1.00 per million tokens on MiniMax M3 428B while H200 runs $0.62. H200 is the cheaper choice by 61%.
On MiniMax M3 428B at 122 tok/s/user, the per-million math comes out to $2.86 for GB200 NVL72 and $0.95 for H200; H200 delivers 201% 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): GB200 NVL72 $2.21/GPU/hr · H200 $1.41/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:$0.382H200:$0.394 | GB200 NVL72:$0.996H200:$0.618 | GB200 NVL72:$2.862H200:$0.951 |
| Concurrency | GB200 NVL72:~180H200:~42 | GB200 NVL72:~74H200:~16 | GB200 NVL72:~18H200:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.