gpt-oss 120B — MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (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.
MI300X edges MI325X at 50 tok/s/user on gpt-oss 120B — $0.08 per million tokens versus $0.13, a 60% cost-per-token gap.
Push gpt-oss 120B to 71 tok/s/user and MI300X lands at $0.10 per million tokens against MI325X's $0.17 — MI300X pulls ahead by 67%.
MI300X: $0.15 per million tokens. MI325X: $0.33. Both at 92 tok/s/user on gpt-oss 120B, with MI300X 124% 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): MI300X $1.12/GPU/hr · MI325X $1.28/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 | MI300X:$0.081MI325X:$0.130 | MI300X:$0.102MI325X:$0.170 | MI300X:$0.148MI325X:$0.331 |
| Concurrency | MI300X:~64MI325X:~64 | MI300X:~49MI325X:~63 | MI300X:~23MI325X:~26 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.