MiniMax M3 428B — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (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.
Near the low end of the 13–198 tok/s/user interactivity band — at 59 tok/s/user — B300 runs $0.39 per million tokens on MiniMax M3 428B while H200 runs $0.46. B300 is the cheaper choice by 17%.
On MiniMax M3 428B at 106 tok/s/user, the per-million math comes out to $1.42 for B300 and $0.80 for H200; H200 delivers 78% more output per dollar.
At 152 tok/s/user on MiniMax M3 428B, B300 costs $2.83 per million tokens; H200 costs $1.16. H200 is 144% 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): B300 $2.34/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 | B300:$0.392H200:$0.457 | B300:$1.421H200:$0.798 | B300:$2.833H200:$1.161 |
| Concurrency | B300:~63H200:~31 | B300:~20H200:~10 | B300:~7H200:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.