Kimi K2.5/K2.6 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 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 40 tok/s/user on Kimi K2.5/K2.6 1T, B200 costs $0.98 per million tokens; MI300X costs $4.44. B200 is 353% more cost-efficient at this operating point.
B200 edges MI300X at 43 tok/s/user on Kimi K2.5/K2.6 1T — $1.05 per million tokens versus $5.09, a 384% cost-per-token gap.
Push Kimi K2.5/K2.6 1T to 46 tok/s/user and B200 lands at $1.13 per million tokens against MI300X's $5.81 — B200 pulls ahead by 415%. (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:$0.980MI300X:$4.441 | B200:$1.052MI300X:$5.089 | B200:$1.128MI300X:$5.813 |
| Concurrency | B200:~58MI300X:~7 | B200:~51MI300X:~6 | B200:~44MI300X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.