DeepSeek V4.1 Flash 552B — MI300X vs MI325X Performance per Dollar
Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (AMD CDNA 3) on DeepSeek V4.1 Flash 552B. Large-hyperscaler-volume ownership TCO normalized by total 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 15–204 tok/s/user interactivity band — at 62 tok/s/user — MI300X runs $0.03 per million tokens on DeepSeek V4.1 Flash 552B while MI325X runs $0.02. MI325X is the cheaper choice by 36%.
On DeepSeek V4.1 Flash 552B at 110 tok/s/user, the per-million math comes out to $0.05 for MI300X and $0.03 for MI325X; MI325X delivers 44% more total tokens per dollar.
At 157 tok/s/user on DeepSeek V4.1 Flash 552B, MI300X costs $0.07 per million tokens; MI325X costs $0.07. MI300X is 6% more cost-efficient at this operating point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI300X $0.95/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | MI300X:$0.027MI325X:$0.020 | MI300X:$0.046MI325X:$0.032 | MI300X:$0.069MI325X:$0.073 |
| Concurrency | MI300X:~8MI325X:~6 | MI300X:~4MI325X:~3 | MI300X:~1MI325X:~2 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.