Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B200 (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.
On Kimi K2.5/K2.6/K2.7-Code 1T at 64 tok/s/user, the per-million math comes out to $0.63 for B200 and $0.57 for GB300 NVL72; GB300 NVL72 delivers 11% more output per dollar.
At 94 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, B200 costs $1.12 per million tokens; GB300 NVL72 costs $1.83. B200 is 64% more cost-efficient at this operating point.
B200 edges GB300 NVL72 at 124 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $2.03 per million tokens versus $3.54, a 74% cost-per-token gap. (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 · 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 | B200:$0.629GB300 NVL72:$0.566 | B200:$1.117GB300 NVL72:$1.830 | B200:$2.033GB300 NVL72:$3.540 |
| Concurrency | B200:~29GB300 NVL72:~464 | B200:~10GB300 NVL72:~73 | B200:~4GB300 NVL72:~29 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.