gpt-oss 120B — Jalapeño vs MI355X Performance per Dollar
Cost per million tokens of Jalapeño (OpenAI Jalapeño) versus MI355X (AMD CDNA 4) 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.
At 149 tok/s/user on gpt-oss 120B, Jalapeño costs $0.01 per million tokens; MI355X costs $0.03. Jalapeño is 324% more cost-efficient at this operating point.
Jalapeño edges MI355X at 201 tok/s/user on gpt-oss 120B — $0.01 per million tokens versus $0.04, a 498% cost-per-token gap.
Push gpt-oss 120B to 253 tok/s/user and Jalapeño lands at $0.01 per million tokens against MI355X's $0.12 — Jalapeño pulls ahead by 1555%. (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 · 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 | Jalapeño:$0.006MI355X:$0.026 | Jalapeño:$0.007MI355X:$0.040 | Jalapeño:$0.007MI355X:$0.122 |
| Concurrency | Jalapeño:~1132MI355X:~12 | Jalapeño:~662MI355X:~5 | Jalapeño:~416MI355X:~15 |