Kimi K2.5/K2.6 1T — B200 vs B300 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (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 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 1T while B300 runs $0.70. B200 is the cheaper choice by 2%.
On Kimi K2.5/K2.6 1T at 102 tok/s/user, the per-million math comes out to $1.30 for B200 and $0.72 for B300; B300 delivers 81% more output per dollar.
At 136 tok/s/user on Kimi K2.5/K2.6 1T, B200 costs $2.73 per million tokens; B300 costs $1.23. B300 is 123% 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 · B300 $2.34/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:$0.684B300:$0.697 | B200:$1.303B300:$0.721 | B200:$2.733B300:$1.225 |
| Concurrency | B200:~24B300:~28 | B200:~8B300:~19 | B200:~3B300:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.