GLM 5/5.1 — H200 vs MI355X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) 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.
H200: $1.19 per million tokens. MI355X: $0.54. Both at 41 tok/s/user on GLM 5/5.1, with MI355X 120% cheaper.
Around the middle of the 21–101 tok/s/user interactivity band — at 61 tok/s/user — H200 runs $1.85 per million tokens on GLM 5/5.1 while MI355X runs $1.11. MI355X is the cheaper choice by 67%.
On GLM 5/5.1 at 82 tok/s/user, the per-million math comes out to $2.93 for H200 and $1.81 for MI355X; MI355X delivers 62% more output per dollar. (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): H200 $1.41/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 | H200:$1.190MI355X:$0.541 | H200:$1.847MI355X:$1.107 | H200:$2.933MI355X:$1.815 |
| Concurrency | H200:~34MI355X:~72 | H200:~14MI355X:~12 | H200:~7MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.