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: $0.18 per million tokens. MI325X: $2.22. Both at 23 tok/s/user on GLM 5/5.1, with GB300 NVL72 1129% cheaper.
Around the middle of the 19–34 tok/s/user interactivity band — at 27 tok/s/user — GB300 NVL72 runs $0.18 per million tokens on GLM 5/5.1 while MI325X runs $4.34. GB300 NVL72 is the cheaper choice by 2253%.
On GLM 5/5.1 at 30 tok/s/user, the per-million math comes out to $0.19 for GB300 NVL72 and $5.71 for MI325X; GB300 NVL72 delivers 2899% more output per dollar. (Numbers reflect the default 1k/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): 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:$0.180MI325X:$2.218 | GB300 NVL72:$0.184MI325X:$4.337 | GB300 NVL72:$0.190MI325X:$5.710 |
| Concurrency | GB300 NVL72:~7423MI325X:~30 | GB300 NVL72:~6952MI325X:~15 | GB300 NVL72:~6351MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.