GLM 5/5.1 · Performance per Dollar

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 41 tok/s/user on GLM 5/5.1, GB300 NVL72 costs $0.23 per million tokens; MI355X costs $0.85. GB300 NVL72 is 265% more cost-efficient at this operating point.

GB300 NVL72 edges MI355X at 50 tok/s/user on GLM 5/5.1 — $1.04 per million tokens versus $1.38, a 33% cost-per-token gap.

Push GLM 5/5.1 to 58 tok/s/user and GB300 NVL72 lands at $1.68 per million tokens against MI355X's $2.11 — GB300 NVL72 pulls ahead by 26%. (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.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
GB300 NVL72:$0.234MI355X:$0.854
GB300 NVL72:$1.035MI355X:$1.376
GB300 NVL72:$1.683MI355X:$2.114
Concurrency
GB300 NVL72:~3055MI355X:~23
GB300 NVL72:~512MI355X:~12
GB300 NVL72:~343MI355X:~7

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.