Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs MI300X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) on Kimi K2.5/K2.6/K2.7-Code 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.
B200: $1.06 per million tokens. MI300X: $4.44. Both at 40 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B200 321% cheaper.
Around the middle of the 37–48 tok/s/user interactivity band — at 43 tok/s/user — B200 runs $1.15 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while MI300X runs $5.09. B200 is the cheaper choice by 344%.
On Kimi K2.5/K2.6/K2.7-Code 1T at 46 tok/s/user, the per-million math comes out to $1.24 for B200 and $5.81 for MI300X; B200 delivers 368% more output per dollar. (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): B200 $1.95/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 | B200:$1.055MI300X:$4.441 | B200:$1.147MI300X:$5.089 | B200:$1.242MI300X:$5.813 |
| Concurrency | B200:~55MI300X:~7 | B200:~47MI300X:~6 | B200:~40MI300X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.