Kimi K2.5/K2.6 1T — B200 vs H200 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Kimi K2.5/K2.6 1T. 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 Kimi K2.5/K2.6 1T at 55 tok/s/user, the per-million math comes out to $1.41 for B200 and $1.33 for H200; H200 delivers 6% more output per dollar.
At 72 tok/s/user on Kimi K2.5/K2.6 1T, B200 costs $2.17 per million tokens; H200 costs $1.79. H200 is 21% more cost-efficient at this operating point.
H200 edges B200 at 89 tok/s/user on Kimi K2.5/K2.6 1T — $2.56 per million tokens versus $3.21, a 26% cost-per-token gap. (Numbers reflect the default 1k/1k · int4 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:$1.410H200:$1.328 | B200:$2.168H200:$1.795 | B200:$3.208H200:$2.556 |
| Concurrency | B200:~29H200:~21 | B200:~14H200:~12 | B200:~8H200:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.