Kimi K3 2.8T — GB200 NVL72 vs GB300 NVL72 Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus GB300 NVL72 (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.
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 →
GB300 NVL72 edges GB200 NVL72 at 54 tok/s/user on Kimi K3 2.8T — $0.08 per million tokens versus $0.12, a 51% cost-per-token gap.
Push Kimi K3 2.8T to 102 tok/s/user and GB200 NVL72 lands at $0.23 per million tokens against GB300 NVL72's $0.12 — GB300 NVL72 pulls ahead by 92%.
GB200 NVL72: $0.41 per million tokens. GB300 NVL72: $0.18. Both at 150 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 126% cheaper. (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): GB200 NVL72 $1.86/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 | GB200 NVL72:$0.121GB300 NVL72:$0.080 | GB200 NVL72:$0.234GB300 NVL72:$0.122 | GB200 NVL72:$0.414GB300 NVL72:$0.183 |
| Concurrency | GB200 NVL72:~16GB300 NVL72:~64 | GB200 NVL72:~10GB300 NVL72:~37 | GB200 NVL72:~3GB300 NVL72:~10 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.