gpt-oss 120B · Performance per Dollar

gpt-oss 120B — MI325X vs MI355X Performance per Dollar

Cost per million tokens of MI325X (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.

MI325X: $0.22 per million tokens. MI355X: $0.03. Both at 75 tok/s/user on gpt-oss 120B, with MI355X 750% cheaper.

Around the middle of the 63–112 tok/s/user interactivity band — at 88 tok/s/user — MI325X runs $0.32 per million tokens on gpt-oss 120B while MI355X runs $0.03. MI355X is the cheaper choice by 930%.

On gpt-oss 120B at 100 tok/s/user, the per-million math comes out to $0.44 for MI325X and $0.04 for MI355X; MI355X delivers 1047% more output per dollar. (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): MI325X $1.28/GPU/hr · MI355X $1.48/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
MI325X:$0.216MI355X:$0.025
MI325X:$0.324MI355X:$0.031
MI325X:$0.443MI355X:$0.039
Concurrency
MI325X:~52MI355X:~114
MI325X:~25MI355X:~78
MI325X:~17MI355X:~54

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.