Kimi K3 2.8T — B300 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on Kimi K3 2.8T. Large-hyperscaler-volume ownership TCO normalized by total 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Push Kimi K3 2.8T to 64 tok/s/user and B300 lands at $0.12 per million tokens against GB300 NVL72's $0.05 — GB300 NVL72 pulls ahead by 149%.
B300: $0.17 per million tokens. GB300 NVL72: $0.07. Both at 111 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 138% cheaper.
Toward the upper edge of the 19–202 tok/s/user interactivity band — at 157 tok/s/user — B300 runs $0.30 per million tokens on Kimi K3 2.8T while GB300 NVL72 runs $0.11. GB300 NVL72 is the cheaper choice by 187%. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): B300 $2.26/chip/hr · GB300 NVL72 $2.31/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.121GB300 NVL72:$0.049 | B300:$0.170GB300 NVL72:$0.071 | B300:$0.304GB300 NVL72:$0.106 |
| Concurrency | B300:~8GB300 NVL72:~53 | B300:~5GB300 NVL72:~48 | B300:~1GB300 NVL72:~29 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.