Kimi K2.5/K2.6 1T — B300 vs MI325X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) 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.
Push Kimi K2.5/K2.6 1T to 33 tok/s/user and B300 lands at $0.84 per million tokens against MI325X's $2.79 — B300 pulls ahead by 234%.
B300: $1.02 per million tokens. MI325X: $3.80. Both at 39 tok/s/user on Kimi K2.5/K2.6 1T, with B300 272% cheaper.
Toward the upper edge of the 28–51 tok/s/user interactivity band — at 45 tok/s/user — B300 runs $1.28 per million tokens on Kimi K2.5/K2.6 1T while MI325X runs $5.25. B300 is the cheaper choice by 310%. (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): B300 $2.34/GPU/hr · MI325X $1.28/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:$0.836MI325X:$2.789 | B300:$1.020MI325X:$3.800 | B300:$1.281MI325X:$5.251 |
| Concurrency | B300:~64MI325X:~16 | B300:~64MI325X:~10 | B300:~32MI325X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.