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 66 tok/s/user on MiniMax M3 428B, B300 costs $0.09 per million tokens; GB200 NVL72 costs $0.13. B300 is 40% more cost-efficient at this operating point.
B300 edges GB200 NVL72 at 106 tok/s/user on MiniMax M3 428B — $0.14 per million tokens versus $0.27, a 89% cost-per-token gap.
Push MiniMax M3 428B to 147 tok/s/user and B300 lands at $0.20 per million tokens against GB200 NVL72's $0.64 — B300 pulls ahead by 226%. (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 · GB200 NVL72 $1.86/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:$0.091GB200 NVL72:$0.128 | B300:$0.143GB200 NVL72:$0.270 | B300:$0.195GB200 NVL72:$0.637 |
| Concurrency | B300:~50GB200 NVL72:~222 | B300:~21GB200 NVL72:~45 | B300:~11GB200 NVL72:~13 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.