Kimi K2.5/K2.6/K2.7-Code 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/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.
GB200 NVL72 edges B300 at 69 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.11 per million tokens versus $0.70, a 547% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 104 tok/s/user and B300 lands at $0.72 per million tokens against GB200 NVL72's $1.45 — B300 pulls ahead by 100%.
B300: $1.32 per million tokens. GB200 NVL72: $2.79. Both at 138 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B300 111% cheaper. (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:$0.698GB200 NVL72:$0.108 | B300:$0.723GB200 NVL72:$1.446 | B300:$1.323GB200 NVL72:$2.789 |
| Concurrency | B300:~28GB200 NVL72:~1936 | B300:~19GB200 NVL72:~89 | B300:~7GB200 NVL72:~30 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.