MiniMax M2.5/M2.7 · Performance per dollar
MiniMax M2.5/M2.7 — GB200 NVL72 vs H200 performance per dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on MiniMax M2.5/M2.7. Large-hyperscaler-volume ownership TCO normalized by total 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 56 tok/s/user on MiniMax M2.5/M2.7, GB200 NVL72 costs $0.070 per million tokens; H200 costs $0.14. GB200 NVL72 is 108% more cost-efficient at this operating point.
GB200 NVL72 edges H200 at 81 tok/s/user on MiniMax M2.5/M2.7 — $0.16 per million tokens versus $0.21, a 35% cost-per-token gap.
Push MiniMax M2.5/M2.7 to 106 tok/s/user and GB200 NVL72 lands at $0.25 per million tokens against H200's $0.38 — GB200 NVL72 pulls ahead by 49%. (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): GB200 NVL72 $1.86/chip/hr · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per million tokens | GB200 NVL72$0.070H200$0.145 | GB200 NVL72$0.158H200$0.213 | GB200 NVL72$0.255H200$0.379 |
| Concurrency | GB200 NVL72~92H200~19 | GB200 NVL72~30H200~9 | GB200 NVL72~14H200~4 |