MiniMax M3 428B — B200 vs H100 Performance per Dollar
Cost per million tokens of B200 (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.
Near the low end of the 15–198 tok/s/user interactivity band — at 61 tok/s/user — B200 runs $0.69 per million tokens on MiniMax M3 428B while H100 runs $0.50. H100 is the cheaper choice by 37%.
On MiniMax M3 428B at 107 tok/s/user, the per-million math comes out to $1.63 for B200 and $1.13 for H100; H100 delivers 44% more output per dollar.
At 153 tok/s/user on MiniMax M3 428B, B200 costs $4.32 per million tokens; H100 costs $1.67. H100 is 159% more cost-efficient at this operating point. (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): B200 $1.95/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 | B200:$0.687H100:$0.503 | B200:$1.627H100:$1.131 | B200:$4.319H100:$1.668 |
| Concurrency | B200:~29H100:~52 | B200:~8H100:~13 | B200:~4H100:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.