GLM 5/5.1 — B200 vs MI325X Performance per Dollar
Cost per million tokens of B200 (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.
Near the low end of the 17–34 tok/s/user interactivity band — at 21 tok/s/user — B200 runs $0.24 per million tokens on GLM 5/5.1 while MI325X runs $1.77. B200 is the cheaper choice by 631%.
On GLM 5/5.1 at 26 tok/s/user, the per-million math comes out to $0.46 for B200 and $3.02 for MI325X; B200 delivers 562% more output per dollar.
At 30 tok/s/user on GLM 5/5.1, B200 costs $0.72 per million tokens; MI325X costs $4.96. B200 is 588% more cost-efficient at this operating point. (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.)
Chip pricing (owning hyperscaler): B200 $1.73/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B200:$0.242MI325X:$1.768 | B200:$0.456MI325X:$3.016 | B200:$0.722MI325X:$4.964 |
| Concurrency | B200:~1254MI325X:~34 | B200:~757MI325X:~16 | B200:~413MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.