GLM 5.3 744B — MI325X vs TPU7x Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) versus TPU7x (Google Ironwood) on GLM 5.3 744B. 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 →
MI325X: $0.24 per million tokens. TPU7x: $0.02. Both at 33 tok/s/user on GLM 5.3 744B, with TPU7x 1258% cheaper.
Around the middle of the 21–71 tok/s/user interactivity band — at 46 tok/s/user — MI325X runs $0.27 per million tokens on GLM 5.3 744B while TPU7x runs $0.02. TPU7x is the cheaper choice by 1148%.
On GLM 5.3 744B at 59 tok/s/user, the per-million math comes out to $0.29 for MI325X and $0.03 for TPU7x; TPU7x delivers 995% more total tokens per dollar. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI325X $1.10/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 | MI325X:$0.244TPU7x:$0.018 | MI325X:$0.267TPU7x:$0.021 | MI325X:$0.290TPU7x:$0.027 |
| Concurrency | MI325X:~3TPU7x:~31 | MI325X:~2TPU7x:~21 | MI325X:~1TPU7x:~16 |