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 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.
On MiniMax M2.5/M2.7 at 60 tok/s/user, the per-million math comes out to $0.54 for H100 and $0.38 for H200; H200 delivers 41% more total tokens per dollar.
At 79 tok/s/user on MiniMax M2.5/M2.7, H100 costs $0.92 per million tokens; H200 costs $0.61. H200 is 50% more cost-efficient at this operating point.
H200 edges H100 at 98 tok/s/user on MiniMax M2.5/M2.7 — $0.91 per million tokens versus $1.57, a 73% 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.)
Chip pricing (owning hyperscaler): H100 $1.17/chip/hr · H200 $1.22/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 | H100:$0.542H200:$0.385 | H100:$0.921H200:$0.615 | H100:$1.569H200:$0.905 |
| Concurrency | H100:~41H200:~30 | H100:~18H200:~15 | H100:~9H200:~8 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
MiniMax M2.5/2.7 230B 8K / 1K Cost per Million Total Tokens vs. Interactivity
MiniMax M2.5/2.7 230B 8K / 1K Cost per Million Total Tokens vs. Interactivity- Cost Tier:
- Owning Hyperscaler
- Source:
- SemiAnalysis InferenceX™
TCO $/chip/hr: VR200: 3.61H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68Jalapeño (Teacup): 1.47
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip