Kimi K2.5/K2.6/K2.7-Code 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/K2.7-Code 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.
Near the low end of the 35–169 tok/s/user interactivity band — at 68 tok/s/user — B200 runs $0.68 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while GB200 NVL72 runs $0.10. GB200 NVL72 is the cheaper choice by 569%.
On Kimi K2.5/K2.6/K2.7-Code 1T at 102 tok/s/user, the per-million math comes out to $1.30 for B200 and $1.41 for GB200 NVL72; B200 delivers 8% more output per dollar.
At 136 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, B200 costs $2.73 per million tokens; GB200 NVL72 costs $2.66. GB200 NVL72 is 3% more cost-efficient at this operating point. (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:$0.102 | B200:$1.303GB200 NVL72:$1.407 | B200:$2.733GB200 NVL72:$2.657 |
| Concurrency | B200:~24GB200 NVL72:~2093 | B200:~8GB200 NVL72:~98 | B200:~3GB200 NVL72:~31 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.