GLM 5/5.1 — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (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.
MI355X edges B200 at 34 tok/s/user on GLM 5/5.1 — $0.45 per million tokens versus $0.86, a 89% cost-per-token gap.
Push GLM 5/5.1 to 57 tok/s/user and B200 lands at $1.47 per million tokens against MI355X's $1.04 — MI355X pulls ahead by 42%.
B200: $2.48 per million tokens. MI355X: $1.65. Both at 80 tok/s/user on GLM 5/5.1, with MI355X 50% cheaper. (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): B200 $1.95/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 | B200:$0.856MI355X:$0.453 | B200:$1.466MI355X:$1.036 | B200:$2.481MI355X:$1.650 |
| Concurrency | B200:~198MI355X:~128 | B200:~25MI355X:~14 | B200:~11MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.