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

Kimi K2.5/K2.6 1T — MI300X vs MI325X Performance per Dollar

Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (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.

At 24 tok/s/user on Kimi K2.5/K2.6 1T, MI300X costs $2.63 per million tokens; MI325X costs $2.50. MI325X is 5% more cost-efficient at this operating point.

MI325X edges MI300X at 32 tok/s/user on Kimi K2.5/K2.6 1T — $2.72 per million tokens versus $3.22, a 18% cost-per-token gap.

Push Kimi K2.5/K2.6 1T to 40 tok/s/user and MI300X lands at $4.44 per million tokens against MI325X's $4.03 — MI325X pulls ahead by 10%. (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): MI300X $1.12/GPU/hr · MI325X $1.28/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
MI300X:$2.627MI325X:$2.495
MI300X:$3.224MI325X:$2.721
MI300X:$4.441MI325X:$4.028
Concurrency
MI300X:~20MI325X:~24
MI300X:~12MI325X:~17
MI300X:~7MI325X:~9

Inference Performance

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