gpt-oss 120B — Jalapeño vs MI325X Performance per Dollar
Cost per million tokens of Jalapeño (OpenAI Jalapeño) versus MI325X (AMD CDNA 3) on gpt-oss 120B. 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.
Jalapeño: $0.01 per million tokens. MI325X: $0.32. Both at 100 tok/s/user on gpt-oss 120B, with Jalapeño 5305% cheaper.
Around the middle of the 98–107 tok/s/user interactivity band — at 102 tok/s/user — Jalapeño runs $0.01 per million tokens on gpt-oss 120B while MI325X runs $0.36. Jalapeño is the cheaper choice by 6046%.
On gpt-oss 120B at 105 tok/s/user, the per-million math comes out to $0.01 for Jalapeño and $0.49 for MI325X; Jalapeño delivers 8219% more total tokens per dollar. (Numbers reflect the default 8k/1k · fp4 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:$0.006MI325X:$0.320 | Jalapeño:$0.006MI325X:$0.364 | Jalapeño:$0.006MI325X:$0.494 |
| Concurrency | Jalapeño:~1993MI325X:~5 | Jalapeño:~1954MI325X:~4 | Jalapeño:~1896MI325X:~4 |