MiniMax M2.5/M2.7 — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) on MiniMax M2.5/M2.7. 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 40–116 tok/s/user interactivity band — at 59 tok/s/user — B300 runs $0.19 per million tokens on MiniMax M2.5/M2.7 while H100 runs $0.57. B300 is the cheaper choice by 199%.
On MiniMax M2.5/M2.7 at 78 tok/s/user, the per-million math comes out to $0.37 for B300 and $0.94 for H100; B300 delivers 156% more output per dollar.
At 97 tok/s/user on MiniMax M2.5/M2.7, B300 costs $0.59 per million tokens; H100 costs $1.75. B300 is 198% 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 · 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 | B300:$0.191H100:$0.572 | B300:$0.367H100:$0.939 | B300:$0.588H100:$1.754 |
| Concurrency | B300:~118H100:~43 | B300:~47H100:~12 | B300:~22H100:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.