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

Kimi K2.5/K2.6 1T — B300 vs MI300X Performance per Dollar

Cost per million tokens of B300 (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.

B300 edges MI300X at 33 tok/s/user on Kimi K2.5/K2.6 1T — $0.84 per million tokens versus $3.34, a 300% cost-per-token gap.

Push Kimi K2.5/K2.6 1T to 38 tok/s/user and B300 lands at $0.98 per million tokens against MI300X's $4.07 — B300 pulls ahead by 316%.

B300: $1.25 per million tokens. MI300X: $5.32. Both at 44 tok/s/user on Kimi K2.5/K2.6 1T, with B300 326% cheaper. (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 · MI300X $1.12/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
B300:$0.836MI300X:$3.342
B300:$0.978MI300X:$4.070
B300:$1.250MI300X:$5.324
Concurrency
B300:~64MI300X:~12
B300:~64MI300X:~8
B300:~32MI300X:~6

Inference Performance

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