Kimi K2.5/K2.6 1T — B200 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) 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 edges B200 at 68 tok/s/user on Kimi K2.5/K2.6 1T — $0.43 per million tokens versus $0.68, a 58% cost-per-token gap.
Push Kimi K2.5/K2.6 1T to 102 tok/s/user and B200 lands at $1.30 per million tokens against GB200 NVL72's $1.14 — GB200 NVL72 pulls ahead by 14%.
B200: $2.73 per million tokens. GB200 NVL72: $3.99. Both at 136 tok/s/user on Kimi K2.5/K2.6 1T, with B200 46% cheaper. (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): B200 $1.95/GPU/hr · GB200 NVL72 $2.21/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:$0.684GB200 NVL72:$0.433 | B200:$1.303GB200 NVL72:$1.143 | B200:$2.733GB200 NVL72:$3.987 |
| Concurrency | B200:~24GB200 NVL72:~511 | B200:~8GB200 NVL72:~119 | B200:~3GB200 NVL72:~15 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.