DeepSeek R1 — Jalapeño vs MI325X Performance per Dollar
Cost per million tokens of Jalapeño (OpenAI Jalapeño) versus MI325X (AMD CDNA 3) 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.
At 35 tok/s/user on DeepSeek R1, MI325X comes in at $0.32 per million tokens. Jalapeño hasn't been benchmarked at this operating point.
Only MI325X has cost data at 57 tok/s/user on DeepSeek R1 — $0.41 per million tokens. Jalapeño is unmeasured at this target.
MI325X costs $0.50 per million tokens at 78 tok/s/user on DeepSeek R1; we have no Jalapeño benchmark data at this exact target. (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): Jalapeño $1.27/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 | Jalapeño:—MI325X:$0.316 | Jalapeño:—MI325X:$0.409 | Jalapeño:—MI325X:$0.504 |
| Concurrency | Jalapeño:—MI325X:~24 | Jalapeño:—MI325X:~11 | Jalapeño:—MI325X:~7 |