MiniMax M2.5/M2.7 — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) 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.
At 69 tok/s/user on MiniMax M2.5/M2.7, B300 costs $0.10 per million tokens; GB300 NVL72 costs $0.08. GB300 NVL72 is 15% more cost-efficient at this operating point.
B300 edges GB300 NVL72 at 108 tok/s/user on MiniMax M2.5/M2.7 — $0.23 per million tokens versus $0.24, a 3% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 147 tok/s/user and B300 lands at $0.62 per million tokens against GB300 NVL72's $0.73 — B300 pulls ahead by 18%. (Numbers reflect the default 1k/1k · fp4 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:$0.097GB300 NVL72:$0.084 | B300:$0.233GB300 NVL72:$0.241 | B300:$0.618GB300 NVL72:$0.727 |
| Concurrency | B300:~395GB300 NVL72:~1024 | B300:~72GB300 NVL72:~121 | B300:~9GB300 NVL72:~22 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.