GLM 5/5.1 · Performance per Dollar

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.

MI325X costs $2.08 per million tokens at 21 tok/s/user on GLM 5/5.1; we have no GB300 NVL72 benchmark data at this exact target.

At 26 tok/s/user on GLM 5/5.1, MI325X comes in at $3.53 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point.

Only MI325X has cost data at 30 tok/s/user on GLM 5/5.1 — $5.71 per million tokens. GB300 NVL72 is unmeasured at this target. (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.

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:MI325X:$2.081
GB300 NVL72:MI325X:$3.534
GB300 NVL72:MI325X:$5.710
Concurrency
GB300 NVL72:MI325X:~34
GB300 NVL72:MI325X:~16
GB300 NVL72:MI325X:~9

Inference Performance

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