Kimi K2.5/K2.6 1T · Performance per Dollar

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 25–113 tok/s/user interactivity band — at 47 tok/s/user — GB200 NVL72 runs $0.13 per million tokens on Kimi K2.5/K2.6 1T while MI355X runs $0.58. GB200 NVL72 is the cheaper choice by 334%.

On Kimi K2.5/K2.6 1T at 69 tok/s/user, the per-million math comes out to $0.45 for GB200 NVL72 and $0.75 for MI355X; GB200 NVL72 delivers 67% 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.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
GB200 NVL72:$0.134MI355X:$0.582
GB200 NVL72:$0.448MI355X:$0.750
GB200 NVL72:$0.854MI355X:$0.982
Concurrency
GB200 NVL72:~1131MI355X:~32
GB200 NVL72:~430MI355X:~17
GB200 NVL72:~155MI355X:~9

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.