MiniMax M3.1 Flash 428B — H100 vs MI355X Performance per Dollar
Cost per million tokens of H100 (NVIDIA Hopper) versus MI355X (AMD CDNA 4) on MiniMax M3.1 Flash 428B. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 34–288 tok/s/user interactivity band — at 97 tok/s/user — H100 runs $0.06 per million tokens on MiniMax M3.1 Flash 428B while MI355X runs $0.01. MI355X is the cheaper choice by 594%.
On MiniMax M3.1 Flash 428B at 161 tok/s/user, the per-million math comes out to $0.08 for H100 and $0.02 for MI355X; MI355X delivers 308% more total tokens per dollar.
At 224 tok/s/user on MiniMax M3.1 Flash 428B, H100 costs $0.10 per million tokens; MI355X costs $0.02. MI355X is 297% more cost-efficient at this operating point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): H100 $1.17/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 | H100:$0.058MI355X:$0.008 | H100:$0.076MI355X:$0.018 | H100:$0.096MI355X:$0.024 |
| Concurrency | H100:~8MI355X:~32 | H100:~7MI355X:~13 | H100:~3MI355X:~9 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.