DeepSeek R1 — MI325X vs MI355X Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) versus MI355X (AMD CDNA 4) on DeepSeek R1. 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.
Near the low end of the 15–53 tok/s/user interactivity band — at 25 tok/s/user — MI325X runs $0.35 per million tokens on DeepSeek R1 while MI355X runs $0.12. MI355X is the cheaper choice by 195%.
On DeepSeek R1 at 34 tok/s/user, the per-million math comes out to $0.43 for MI325X and $0.17 for MI355X; MI355X delivers 159% more total tokens per dollar.
At 44 tok/s/user on DeepSeek R1, MI325X costs $0.65 per million tokens; MI355X costs $0.19. MI355X is 241% more cost-efficient at this operating point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI325X $1.10/chip/hr · MI355X $1.50/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 | MI325X:$0.354MI355X:$0.120 | MI325X:$0.433MI355X:$0.167 | MI325X:$0.645MI355X:$0.189 |
| Concurrency | MI325X:~33MI355X:~2048 | MI325X:~20MI355X:~64 | MI325X:~11MI355X:~41 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
DeepSeek R1 0528 671B 8K / 1K Cost per Million Total Tokens vs. Interactivity
DeepSeek R1 0528 671B 8K / 1K Cost per Million Total Tokens vs. Interactivity- Cost Tier:
- Source:
- SemiAnalysis InferenceX™
TCO $/chip/hr:
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Matching measurements exist, but their chip series are hidden.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip
1 The ATOM engine is promising, however it has yet to serve production tokens. It is still in its infant stage.