Kimi K3 2.8T — MI355X vs TPU7x Performance per Dollar
Cost per million tokens of MI355X (AMD CDNA 4) 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 →
MI355X: $0.05 per million tokens. TPU7x: $0.05. Both at 62 tok/s/user on Kimi K3 2.8T, with TPU7x 6% cheaper.
Around the middle of the 26–172 tok/s/user interactivity band — at 99 tok/s/user — MI355X runs $0.08 per million tokens on Kimi K3 2.8T while TPU7x runs $0.06. TPU7x is the cheaper choice by 24%.
On Kimi K3 2.8T at 136 tok/s/user, the per-million math comes out to $0.24 for MI355X and $0.09 for TPU7x; TPU7x delivers 176% 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): MI355X $1.50/chip/hr · TPU7x $1.03/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 | MI355X:$0.049TPU7x:$0.046 | MI355X:$0.076TPU7x:$0.061 | MI355X:$0.243TPU7x:$0.088 |
| Concurrency | MI355X:~22TPU7x:~43 | MI355X:~24TPU7x:~26 | MI355X:~11TPU7x:~16 |
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.