GLM 5/5.1 — GB300 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on GLM 5/5.1. 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.
GB300 NVL72 costs $0.11 per million tokens at 69 tok/s/user on GLM 5/5.1; we have no MI325X benchmark data at this exact target.
At 121 tok/s/user on GLM 5/5.1, GB300 NVL72 comes in at $0.91 per million tokens. MI325X hasn't been benchmarked at this operating point.
Only GB300 NVL72 has cost data at 173 tok/s/user on GLM 5/5.1 — $4.87 per million tokens. MI325X is unmeasured at this target. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB300 NVL72 $2.65/GPU/hr · MI325X $1.28/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB300 NVL72:$0.110MI325X:— | GB300 NVL72:$0.910MI325X:— | GB300 NVL72:$4.870MI325X:— |
| Concurrency | GB300 NVL72:~1221MI325X:— | GB300 NVL72:~166MI325X:— | GB300 NVL72:~23MI325X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.