Kimi K2.5/K2.6 1T — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (AMD CDNA 3) 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 34–48 tok/s/user interactivity band — at 37 tok/s/user — H200 runs $0.86 per million tokens on Kimi K2.5/K2.6 1T while MI300X runs $3.90. H200 is the cheaper choice by 354%.
On Kimi K2.5/K2.6 1T at 41 tok/s/user, the per-million math comes out to $0.97 for H200 and $4.65 for MI300X; H200 delivers 381% more output per dollar.
At 45 tok/s/user on Kimi K2.5/K2.6 1T, H200 costs $1.07 per million tokens; MI300X costs $5.57. H200 is 418% more cost-efficient at this operating point. (Numbers reflect the default 1k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): H200 $1.41/GPU/hr · MI300X $1.12/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 | H200:$0.860MI300X:$3.904 | H200:$0.967MI300X:$4.646 | H200:$1.074MI300X:$5.566 |
| Concurrency | H200:~53MI300X:~9 | H200:~42MI300X:~7 | H200:~34MI300X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.