MiniMax M3 428B — B300 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB200 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.
At 62 tok/s/user on MiniMax M3 428B, B300 costs $0.12 per million tokens; GB200 NVL72 costs $0.14. B300 is 16% more cost-efficient at this operating point.
B300 edges GB200 NVL72 at 94 tok/s/user on MiniMax M3 428B — $0.14 per million tokens versus $0.33, a 142% cost-per-token gap.
Push MiniMax M3 428B to 125 tok/s/user and B300 lands at $0.19 per million tokens against GB200 NVL72's $0.78 — B300 pulls ahead by 312%. (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.)
GPU pricing (owning hyperscaler): B300 $2.34/GPU/hr · GB200 NVL72 $2.21/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:$0.124GB200 NVL72:$0.145 | B300:$0.137GB200 NVL72:$0.331 | B300:$0.189GB200 NVL72:$0.780 |
| Concurrency | B300:~166GB200 NVL72:~302 | B300:~24GB200 NVL72:~49 | B300:~14GB200 NVL72:~15 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.