gpt-oss 120B — H200 vs MI300X Performance per Dollar
Cost per million tokens of H200 (NVIDIA Hopper) versus MI300X (AMD CDNA 3) 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.
On gpt-oss 120B at 92 tok/s/user, the per-million math comes out to $0.11 for H200 and $0.15 for MI300X; H200 delivers 38% more output per dollar.
At 144 tok/s/user on gpt-oss 120B, H200 costs $0.19 per million tokens; MI300X costs $0.32. H200 is 68% more cost-efficient at this operating point.
H200 edges MI300X at 197 tok/s/user on gpt-oss 120B — $0.37 per million tokens versus $0.87, a 137% cost-per-token gap. (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 · MI300X $1.12/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:$0.108MI300X:$0.148 | H200:$0.191MI300X:$0.320 | H200:$0.368MI300X:$0.872 |
| Concurrency | H200:~64MI300X:~23 | H200:~63MI300X:~7 | H200:~17MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.