gpt-oss 120B — Jalapeño vs MI300X Performance per Dollar
Cost per million tokens of Jalapeño (OpenAI Jalapeño) versus MI300X (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.
Push gpt-oss 120B to 134 tok/s/user and Jalapeño lands at $0.01 per million tokens against MI300X's $0.07 — Jalapeño pulls ahead by 1108%.
Jalapeño: $0.01 per million tokens. MI300X: $0.14. Both at 172 tok/s/user on gpt-oss 120B, with Jalapeño 2106% cheaper.
Toward the upper edge of the 98–246 tok/s/user interactivity band — at 209 tok/s/user — Jalapeño runs $0.01 per million tokens on gpt-oss 120B while MI300X runs $0.29. Jalapeño is the cheaper choice by 4257%. (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 · MI300X $0.95/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:$0.006MI300X:$0.074 | Jalapeño:$0.006MI300X:$0.141 | Jalapeño:$0.007MI300X:$0.294 |
| Concurrency | Jalapeño:~1366MI300X:~6 | Jalapeño:~863MI300X:~7 | Jalapeño:~622MI300X:~4 |