Kimi K2.5/K2.6/K2.7-Code 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/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: $0.06 per million tokens. MI355X: $0.56. Both at 46 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with GB200 NVL72 823% cheaper.
Around the middle of the 24–113 tok/s/user interactivity band — at 68 tok/s/user — GB200 NVL72 runs $0.10 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while MI355X runs $0.74. GB200 NVL72 is the cheaper choice by 625%.
On Kimi K2.5/K2.6/K2.7-Code 1T at 91 tok/s/user, the per-million math comes out to $1.05 for GB200 NVL72 and $0.98 for MI355X; MI355X delivers 7% more output per dollar. (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:$0.061MI355X:$0.565 | GB200 NVL72:$0.102MI355X:$0.741 | GB200 NVL72:$1.047MI355X:$0.982 |
| Concurrency | GB200 NVL72:~4301MI355X:~35 | GB200 NVL72:~2093MI355X:~17 | GB200 NVL72:~180MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.