GLM 5/5.1 — GB200 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB200 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.
At 29 tok/s/user on GLM 5/5.1, GB200 NVL72 costs $0.13 per million tokens; MI325X costs $3.00. GB200 NVL72 is 2131% more cost-efficient at this operating point.
GB200 NVL72 edges MI325X at 29 tok/s/user on GLM 5/5.1 — $0.13 per million tokens versus $3.00, a 2131% cost-per-token gap.
Push GLM 5/5.1 to 29 tok/s/user and GB200 NVL72 lands at $0.13 per million tokens against MI325X's $3.00 — GB200 NVL72 pulls ahead by 2131%. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB200 NVL72 $2.21/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 | GB200 NVL72:$0.134MI325X:$3.000 | GB200 NVL72:$0.134MI325X:$3.000 | GB200 NVL72:$0.134MI325X:$3.000 |
| Concurrency | GB200 NVL72:~2490MI325X:~4 | GB200 NVL72:~2490MI325X:~4 | GB200 NVL72:~2490MI325X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.