Kimi K2.5/K2.6/K2.7-Code 1T — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 49 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB300 NVL72 costs $0.06 per million tokens; MI355X costs $0.13. GB300 NVL72 is 128% more cost-efficient at this operating point.
GB300 NVL72 edges MI355X at 73 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.09 per million tokens versus $0.18, a 90% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 98 tok/s/user and GB300 NVL72 lands at $0.41 per million tokens against MI355X's $0.25 — MI355X pulls ahead by 65%. (Numbers reflect the default 8k/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): GB300 NVL72 $2.65/GPU/hr · MI355X $1.48/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 | GB300 NVL72:$0.056MI355X:$0.128 | GB300 NVL72:$0.094MI355X:$0.178 | GB300 NVL72:$0.412MI355X:$0.250 |
| Concurrency | GB300 NVL72:~2151MI355X:~30 | GB300 NVL72:~700MI355X:~15 | GB300 NVL72:~76MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.