Kimi K2.5/K2.6 1T · Performance per Dollar

Kimi K2.5/K2.6 1T — GB200 NVL72 vs H200 Performance per Dollar

Cost per million tokens of GB200 NVL72 (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.

GB200 NVL72 costs $0.33 per million tokens at 60 tok/s/user on Kimi K2.5/K2.6 1T; we have no H200 benchmark data at this exact target.

At 103 tok/s/user on Kimi K2.5/K2.6 1T, GB200 NVL72 comes in at $1.18 per million tokens. H200 hasn't been benchmarked at this operating point.

Only GB200 NVL72 has cost data at 146 tok/s/user on Kimi K2.5/K2.6 1T — $4.69 per million tokens. H200 is unmeasured at this target. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/GPU/hr · H200 $1.41/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

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)
Dollar per Million Tokens
GB200 NVL72:$0.328H200:
GB200 NVL72:$1.180H200:
GB200 NVL72:$4.687H200:
Concurrency
GB200 NVL72:~667H200:
GB200 NVL72:~116H200:
GB200 NVL72:~13H200:

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.