GLM 5/5.1 — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 30 tok/s/user on GLM 5/5.1, GB300 NVL72 costs $0.06 per million tokens; MI355X costs $0.45. GB300 NVL72 is 600% more cost-efficient at this operating point.
GB300 NVL72 edges MI355X at 42 tok/s/user on GLM 5/5.1 — $0.07 per million tokens versus $0.90, a 1146% cost-per-token gap.
Push GLM 5/5.1 to 55 tok/s/user and GB300 NVL72 lands at $0.09 per million tokens against MI355X's $1.81 — GB300 NVL72 pulls ahead by 2018%. (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 · MI355X $1.48/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:$0.065MI355X:$0.454 | GB300 NVL72:$0.072MI355X:$0.896 | GB300 NVL72:$0.085MI355X:$1.808 |
| Concurrency | GB300 NVL72:~4301MI355X:~62 | GB300 NVL72:~3770MI355X:~22 | GB300 NVL72:~1946MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.