gpt-oss 120B — H200 vs MI355X Performance per Dollar
Cost per million tokens of H200 (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.
MI355X edges H200 at 120 tok/s/user on gpt-oss 120B — $0.05 per million tokens versus $0.14, a 212% cost-per-token gap.
Push gpt-oss 120B to 170 tok/s/user and H200 lands at $0.26 per million tokens against MI355X's $0.10 — MI355X pulls ahead by 166%.
H200: $0.52 per million tokens. MI355X: $0.18. Both at 220 tok/s/user on gpt-oss 120B, with MI355X 185% cheaper. (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): 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:$0.144MI355X:$0.046 | H200:$0.262MI355X:$0.099 | H200:$0.522MI355X:$0.183 |
| Concurrency | H200:~64MI355X:~38 | H200:~39MI355X:~12 | H200:~7MI355X:~5 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.