Kimi K2.5/K2.6 1T — B300 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B300 (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.
Near the low end of the 45–146 tok/s/user interactivity band — at 70 tok/s/user — B300 runs $0.89 per million tokens on Kimi K2.5/K2.6 1T while GB200 NVL72 runs $0.46. GB200 NVL72 is the cheaper choice by 92%.
On Kimi K2.5/K2.6 1T at 96 tok/s/user, the per-million math comes out to $1.37 for B300 and $0.97 for GB200 NVL72; GB200 NVL72 delivers 42% more output per dollar.
At 121 tok/s/user on Kimi K2.5/K2.6 1T, B300 costs $2.25 per million tokens; GB200 NVL72 costs $3.39. B300 is 51% 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): B300 $2.34/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 | B300:$0.893GB200 NVL72:$0.464 | B300:$1.371GB200 NVL72:$0.968 | B300:$2.247GB200 NVL72:$3.394 |
| Concurrency | B300:~21GB200 NVL72:~372 | B300:~10GB200 NVL72:~136 | B300:~4GB200 NVL72:~16 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.