GLM 5.3 744B — GB200 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB200 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on GLM 5.3 744B. Owning-hyperscaler TCO normalized by output 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 costs $0.38 per million tokens at 8 tok/s/user on GLM 5.3 744B; we have no GB200 NVL72 benchmark data at this exact target.
At 14 tok/s/user on GLM 5.3 744B, MI325X comes in at $0.38 per million tokens. GB200 NVL72 hasn't been benchmarked at this operating point.
Only MI325X has cost data at 21 tok/s/user on GLM 5.3 744B — $0.39 per million tokens. GB200 NVL72 is unmeasured at this target. (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): GB200 NVL72 $1.86/chip/hr · MI325X $1.10/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 | GB200 NVL72:—MI325X:$0.376 | GB200 NVL72:—MI325X:$0.376 | GB200 NVL72:—MI325X:$0.394 |
| Concurrency | GB200 NVL72:—MI325X:~3 | GB200 NVL72:—MI325X:~3 | GB200 NVL72:—MI325X:~2 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.