gpt-oss 120B — MI300X vs MI355X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) 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.
Near the low end of the 71–248 tok/s/user interactivity band — at 115 tok/s/user — MI300X runs $0.21 per million tokens on gpt-oss 120B while MI355X runs $0.04. MI355X is the cheaper choice by 376%.
On gpt-oss 120B at 160 tok/s/user, the per-million math comes out to $0.38 for MI300X and $0.09 for MI355X; MI355X delivers 346% more output per dollar.
At 204 tok/s/user on gpt-oss 120B, MI300X costs $0.99 per million tokens; MI355X costs $0.15. MI355X is 552% more cost-efficient at this operating point. (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 · 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 | MI300X:$0.205MI355X:$0.043 | MI300X:$0.383MI355X:$0.086 | MI300X:$0.992MI355X:$0.152 |
| Concurrency | MI300X:~14MI355X:~42 | MI300X:~5MI355X:~15 | MI300X:~7MI355X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.