MiniMax M3 428B — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (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.
Only B200 has cost data at 148 tok/s/user on MiniMax M3 428B — $0.09 per million tokens. GB300 NVL72 is unmeasured at this target.
B200 costs $0.22 per million tokens at 290 tok/s/user on MiniMax M3 428B; we have no GB300 NVL72 benchmark data at this exact target.
At 432 tok/s/user on MiniMax M3 428B, B200 comes in at $0.58 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B200 $1.73/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 | B200:$0.088GB300 NVL72:— | B200:$0.217GB300 NVL72:— | B200:$0.579GB300 NVL72:— |
| Concurrency | B200:~40GB300 NVL72:— | B200:~4GB300 NVL72:— | B200:~2GB300 NVL72:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.