Kimi K2.5/K2.6 1T — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on Kimi K2.5/K2.6 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.
Near the low end of the 24–113 tok/s/user interactivity band — at 46 tok/s/user — GB200 NVL72 runs $0.12 per million tokens on Kimi K2.5/K2.6 1T while MI355X runs $0.56. GB200 NVL72 is the cheaper choice by 363%.
On Kimi K2.5/K2.6 1T at 68 tok/s/user, the per-million math comes out to $0.43 for GB200 NVL72 and $0.74 for MI355X; GB200 NVL72 delivers 71% more output per dollar.
At 91 tok/s/user on Kimi K2.5/K2.6 1T, GB200 NVL72 costs $0.85 per million tokens; MI355X costs $0.98. GB200 NVL72 is 15% more cost-efficient at this operating point. (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 · 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 | GB200 NVL72:$0.122MI355X:$0.565 | GB200 NVL72:$0.433MI355X:$0.741 | GB200 NVL72:$0.854MI355X:$0.982 |
| Concurrency | GB200 NVL72:~1337MI355X:~35 | GB200 NVL72:~511MI355X:~17 | GB200 NVL72:~155MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.