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: $0.17 per million tokens. GB300 NVL72: $0.15. Both at 125 tok/s/user on MiniMax M3 428B, with GB300 NVL72 14% cheaper.
Around the middle of the 22–436 tok/s/user interactivity band — at 229 tok/s/user — B300 runs $0.27 per million tokens on MiniMax M3 428B while GB300 NVL72 runs $0.36. B300 is the cheaper choice by 32%.
On MiniMax M3 428B at 333 tok/s/user, the per-million math comes out to $0.60 for B300 and $0.62 for GB300 NVL72; B300 delivers 2% more output per dollar. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B300 $2.26/chip/hr · GB300 NVL72 $2.31/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.167GB300 NVL72:$0.147 | B300:$0.272GB300 NVL72:$0.358 | B300:$0.604GB300 NVL72:$0.619 |
| Concurrency | B300:~16GB300 NVL72:~60 | B300:~5GB300 NVL72:~8 | B300:~4GB300 NVL72:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.