Kimi K2.5/K2.6/K2.7-Code 1T — GB200 NVL72 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of GB200 NVL72 (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.
GB200 NVL72 edges GB300 NVL72 at 52 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.07 per million tokens versus $0.16, a 133% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 86 tok/s/user and GB200 NVL72 lands at $0.38 per million tokens against GB300 NVL72's $1.56 — GB200 NVL72 pulls ahead by 307%.
GB200 NVL72: $1.92 per million tokens. GB300 NVL72: $3.22. Both at 120 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with GB200 NVL72 68% 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): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.070GB300 NVL72:$0.163 | GB200 NVL72:$0.382GB300 NVL72:$1.557 | GB200 NVL72:$1.921GB300 NVL72:$3.219 |
| Concurrency | GB200 NVL72:~4255GB300 NVL72:~1198 | GB200 NVL72:~462GB300 NVL72:~92 | GB200 NVL72:~47GB300 NVL72:~33 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.