MiniMax M2.5/M2.7 — B300 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB200 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.
B300: $0.10 per million tokens. GB200 NVL72: $0.07. Both at 68 tok/s/user on MiniMax M2.5/M2.7, with GB200 NVL72 32% cheaper.
Around the middle of the 31–180 tok/s/user interactivity band — at 105 tok/s/user — B300 runs $0.21 per million tokens on MiniMax M2.5/M2.7 while GB200 NVL72 runs $0.19. GB200 NVL72 is the cheaper choice by 10%.
On MiniMax M2.5/M2.7 at 143 tok/s/user, the per-million math comes out to $0.57 for B300 and $0.58 for GB200 NVL72; B300 delivers 3% more output per dollar. (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 · 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:$0.096GB200 NVL72:$0.073 | B300:$0.210GB200 NVL72:$0.190 | B300:$0.566GB200 NVL72:$0.581 |
| Concurrency | B300:~349GB200 NVL72:~928 | B300:~146GB200 NVL72:~236 | B300:~7GB200 NVL72:~45 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.