MiniMax M2.5/M2.7 — H100 vs H200 Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) 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.
On MiniMax M2.5/M2.7 at 59 tok/s/user, the per-million math comes out to $0.57 for H100 and $0.41 for H200; H200 delivers 39% more output per dollar.
At 78 tok/s/user on MiniMax M2.5/M2.7, H100 costs $0.94 per million tokens; H200 costs $0.86. H200 is 9% more cost-efficient at this operating point.
H200 edges H100 at 97 tok/s/user on MiniMax M2.5/M2.7 — $1.41 per million tokens versus $1.75, a 24% cost-per-token gap. (Numbers reflect the default 1k/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): H100 $1.30/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 | H100:$0.572H200:$0.412 | H100:$0.939H200:$0.863 | H100:$1.754H200:$1.413 |
| Concurrency | H100:~43H200:~66 | H100:~12H200:~23 | H100:~8H200:~12 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.