Kimi K2.5/K2.6 1T — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (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.
On Kimi K2.5/K2.6 1T at 61 tok/s/user, the per-million math comes out to $0.74 for B300 and $0.70 for MI355X; MI355X delivers 6% more output per dollar.
At 79 tok/s/user on Kimi K2.5/K2.6 1T, B300 costs $1.06 per million tokens; MI355X costs $0.84. MI355X is 26% more cost-efficient at this operating point.
MI355X edges B300 at 96 tok/s/user on Kimi K2.5/K2.6 1T — $1.09 per million tokens versus $1.37, a 26% cost-per-token gap. (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): B300 $2.34/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 | B300:$0.743MI355X:$0.699 | B300:$1.055MI355X:$0.839 | B300:$1.371MI355X:$1.086 |
| Concurrency | B300:~29MI355X:~20 | B300:~16MI355X:~12 | B300:~10MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.