Kimi K2.5/K2.6/K2.7-Code 1T · Performance per Dollar
Kimi K2.5/K2.6/K2.7-Code 1T — GB200 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) on Kimi K2.5/K2.6/K2.7-Code 1T. Large-hyperscaler-volume ownership TCO normalized by total 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 64 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB200 NVL72 comes in at $0.058 per million tokens. MI300X hasn't been benchmarked at this operating point.
Only GB200 NVL72 has cost data at 103 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.33 per million tokens. MI300X is unmeasured at this target.
GB200 NVL72 costs $0.70 per million tokens at 141 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T; we have no MI300X benchmark data at this exact target. (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.)
Chip pricing (owning hyperscaler): GB200 NVL72 $1.86/chip/hr · MI300X $0.95/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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) |
|---|---|---|---|
| Dollars per Million Tokens | GB200 NVL72$0.058MI300X— | GB200 NVL72$0.33MI300X— | GB200 NVL72$0.70MI300X— |
| Concurrency | GB200 NVL72~1,203MI300X— | GB200 NVL72~167MI300X— | GB200 NVL72~27MI300X— |
