MiniMax M3.1 Flash 428B — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (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 →
Push MiniMax M3.1 Flash 428B to 137 tok/s/user and B300 lands at $0.01 per million tokens against MI355X's $0.01 — MI355X pulls ahead by 44%.
B300: $0.03 per million tokens. MI355X: $0.03. Both at 269 tok/s/user on MiniMax M3.1 Flash 428B, with B300 5% cheaper.
Toward the upper edge of the 6–531 tok/s/user interactivity band — at 400 tok/s/user — B300 runs $0.06 per million tokens on MiniMax M3.1 Flash 428B while MI355X runs $0.05. MI355X is the cheaper choice by 7%. (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): B300 $2.26/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 | B300:$0.010MI355X:$0.007 | B300:$0.026MI355X:$0.027 | B300:$0.058MI355X:$0.055 |
| Concurrency | B300:~42MI355X:~33 | B300:~13MI355X:~8 | B300:~5MI355X:~3 |
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.