gpt-oss 120B — H100 vs MI355X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI355X (AMD CDNA 4) on gpt-oss 120B. 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.
Push gpt-oss 120B to 117 tok/s/user and H100 lands at $0.14 per million tokens against MI355X's $0.05 — MI355X pulls ahead by 172%.
H100: $0.26 per million tokens. MI355X: $0.15. Both at 166 tok/s/user on gpt-oss 120B, with MI355X 76% cheaper.
Toward the upper edge of the 67–266 tok/s/user interactivity band — at 216 tok/s/user — H100 runs $0.49 per million tokens on gpt-oss 120B while MI355X runs $0.23. MI355X is the cheaper choice by 112%. (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): H100 $1.30/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 | H100:$0.139MI355X:$0.051 | H100:$0.262MI355X:$0.149 | H100:$0.487MI355X:$0.230 |
| Concurrency | H100:~64MI355X:~36 | H100:~17MI355X:~30 | H100:~8MI355X:~31 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.