Kimi K3 2.8T — TPU7x vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of TPU7x (Google Ironwood) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 →
Vera Rubin NVL72 edges TPU7x at 174 tok/s/user on Kimi K3 2.8T — $0.03 per million tokens versus $0.15, a 355% cost-per-token gap.
Push Kimi K3 2.8T to 246 tok/s/user and TPU7x lands at $0.23 per million tokens against Vera Rubin NVL72's $0.05 — Vera Rubin NVL72 pulls ahead by 406%.
TPU7x: $0.33 per million tokens. Vera Rubin NVL72: $0.07. Both at 319 tok/s/user on Kimi K3 2.8T, with Vera Rubin NVL72 349% 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): TPU7x $1.03/chip/hr · Vera Rubin NVL72 $3.61/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 | TPU7x:$0.146Vera Rubin NVL72:$0.032 | TPU7x:$0.234Vera Rubin NVL72:$0.046 | TPU7x:$0.329Vera Rubin NVL72:$0.073 |
| Concurrency | TPU7x:~9Vera Rubin NVL72:~156 | TPU7x:~5Vera Rubin NVL72:~66 | TPU7x:~2Vera Rubin NVL72:~51 |
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.