Kimi K2.5/K2.6/K2.7-Code 1T — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 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.
At 64 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, B300 costs $0.69 per million tokens; GB300 NVL72 costs $0.57. GB300 NVL72 is 22% more cost-efficient at this operating point.
B300 edges GB300 NVL72 at 94 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.72 per million tokens versus $1.83, a 156% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 124 tok/s/user and B300 lands at $0.85 per million tokens against GB300 NVL72's $3.54 — B300 pulls ahead by 315%. (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 · GB300 NVL72 $2.65/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:$0.691GB300 NVL72:$0.566 | B300:$0.715GB300 NVL72:$1.830 | B300:$0.854GB300 NVL72:$3.540 |
| Concurrency | B300:~30GB300 NVL72:~464 | B300:~21GB300 NVL72:~73 | B300:~12GB300 NVL72:~29 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.