MiniMax M3.1 Flash 428B · Performance per dollar
MiniMax M3.1 Flash 428B — GB300 NVL72 vs MI355X performance per dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) 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 60–621 tok/s/user interactivity band — at 200 tok/s/user — GB300 NVL72 runs $0.005 per million tokens on MiniMax M3.1 Flash 428B while MI355X runs $0.005. MI355X is the cheaper choice by 2%.
On MiniMax M3.1 Flash 428B at 340 tok/s/user, the per-million math comes out to $0.024 for GB300 NVL72 and $0.011 for MI355X; MI355X delivers 108% more total tokens per dollar.
At 481 tok/s/user on MiniMax M3.1 Flash 428B, GB300 NVL72 costs $0.066 per million tokens; MI355X costs $0.024. MI355X delivers 179% more tokens per dollar 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): GB300 NVL72 $2.31/chip/hr · MI355X $1.50/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollars per million tokens | GB300 NVL72$0.005MI355X$0.005 | GB300 NVL72$0.024MI355X$0.011 | GB300 NVL72$0.066MI355X$0.024 |
| Concurrency | GB300 NVL72~416MI355X~42 | GB300 NVL72~15MI355X~19 | GB300 NVL72~4MI355X~8 |
