Kimi K3 2.8T · Performance per dollar
Kimi K3 2.8T — GB300 NVL72 vs TPU7x performance per dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus TPU7x (Google Ironwood) 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 →
GB300 NVL72: $0.059 per million tokens. TPU7x: $0.077. Both at 123 tok/s/user on Kimi K3 2.8T, with GB300 NVL72 23% cheaper.
Around the middle of the 35–390 tok/s/user interactivity band — at 212 tok/s/user — GB300 NVL72 runs $0.082 per million tokens on Kimi K3 2.8T while TPU7x runs $0.20. GB300 NVL72 is the cheaper choice by 59%.
On Kimi K3 2.8T at 302 tok/s/user, the per-million math comes out to $0.19 for GB300 NVL72 and $0.31 for TPU7x; GB300 NVL72 delivers 64% 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 · TPU7x $1.03/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per million tokens | GB300 NVL72$0.059TPU7x$0.077 | GB300 NVL72$0.082TPU7x$0.20 | GB300 NVL72$0.19TPU7x$0.31 |
| Concurrency | GB300 NVL72~41TPU7x~19 | GB300 NVL72~25TPU7x~6 | GB300 NVL72~16TPU7x~3 |
