MiniMax M3 428B — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) 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.
B300: $0.19 per million tokens. GB300 NVL72: $0.42. Both at 42 tok/s/user on MiniMax M3 428B, with B300 127% cheaper.
Around the middle of the 9–142 tok/s/user interactivity band — at 76 tok/s/user — B300 runs $0.42 per million tokens on MiniMax M3 428B while GB300 NVL72 runs $1.58. B300 is the cheaper choice by 280%.
On MiniMax M3 428B at 109 tok/s/user, the per-million math comes out to $0.78 for B300 and $3.79 for GB300 NVL72; B300 delivers 387% 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): B300 $2.34/GPU/hr · GB300 NVL72 $2.65/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:$0.186GB300 NVL72:$0.423 | B300:$0.416GB300 NVL72:$1.579 | B300:$0.779GB300 NVL72:$3.791 |
| Concurrency | B300:~183GB300 NVL72:~225 | B300:~64GB300 NVL72:~21 | B300:~38GB300 NVL72:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.