Kimi K3 2.8T — GB300 NVL72 vs H200 Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Kimi K3 2.8T. Owning-hyperscaler 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 →
GB300 NVL72: $0.05 per million tokens. H200: $4.85. Both at 63 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 8847% cheaper.
Around the middle of the 2–246 tok/s/user interactivity band — at 124 tok/s/user — GB300 NVL72 runs $0.09 per million tokens on Kimi K3 2.8T while H200 runs $4.85. GB300 NVL72 is the cheaper choice by 5409%.
On Kimi K3 2.8T at 185 tok/s/user, the per-million math comes out to $0.18 for GB300 NVL72 and $4.85 for H200; GB300 NVL72 delivers 2652% more total tokens per dollar. (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): GB300 NVL72 $2.31/chip/hr · H200 $1.22/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 | GB300 NVL72:$0.054H200:$4.850 | GB300 NVL72:$0.088H200:$4.850 | GB300 NVL72:$0.176H200:$4.850 |
| Concurrency | GB300 NVL72:~48H200:~1 | GB300 NVL72:~44H200:~1 | GB300 NVL72:~7H200:~1 |
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.