MiniMax M2.5/M2.7 — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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 43 tok/s/user on MiniMax M2.5/M2.7, B200 costs $0.06 per million tokens; H200 costs $0.14. B200 is 146% more cost-efficient at this operating point.
B200 edges H200 at 72 tok/s/user on MiniMax M2.5/M2.7 — $0.14 per million tokens versus $0.21, a 47% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 102 tok/s/user and B200 lands at $0.26 per million tokens against H200's $0.38 — B200 pulls ahead by 46%. (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): B200 $1.95/GPU/hr · H200 $1.41/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 | B200:$0.056H200:$0.139 | B200:$0.142H200:$0.209 | B200:$0.261H200:$0.381 |
| Concurrency | B200:~582H200:~30 | B200:~32H200:~12 | B200:~15H200:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.