GLM 5/5.1 — GB200 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB200 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.
GB200 NVL72: $0.31 per million tokens. MI355X: $0.35. Both at 37 tok/s/user on GLM 5/5.1, with GB200 NVL72 12% cheaper.
Around the middle of the 29–62 tok/s/user interactivity band — at 45 tok/s/user — GB200 NVL72 runs $0.96 per million tokens on GLM 5/5.1 while MI355X runs $0.40. MI355X is the cheaper choice by 142%.
On GLM 5/5.1 at 54 tok/s/user, the per-million math comes out to $4.50 for GB200 NVL72 and $0.45 for MI355X; MI355X delivers 907% more output per dollar. (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 · 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 | GB200 NVL72:$0.311MI355X:$0.349 | GB200 NVL72:$0.957MI355X:$0.396 | GB200 NVL72:$4.499MI355X:$0.447 |
| Concurrency | GB200 NVL72:~931MI355X:~15 | GB200 NVL72:~150MI355X:~11 | GB200 NVL72:~27MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.