Kimi K3 2.8T · Performance per Dollar
Kimi K3 2.8T — B200 vs B300 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (NVIDIA Blackwell) on Kimi K3 2.8T. 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.
GPU pricing (owning hyperscaler): B200 $1.95/GPU/hr · B300 $2.34/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
No interpolated cost-per-token data available for the default model on this GPU pair. Use the chart controls below to select a model and precision with benchmark data for both GPUs.
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.
Vendor:
Aggregation:
Spec Decoding: