MiniMax M3.1 Flash 428B — B200 vs MI355X Performance per Dollar
Cost per million tokens of B200 (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 →
B200 edges MI355X at 150 tok/s/user on MiniMax M3.1 Flash 428B — $0.01 per million tokens versus $0.02, a 112% cost-per-token gap.
Push MiniMax M3.1 Flash 428B to 268 tok/s/user and B200 lands at $0.02 per million tokens against MI355X's $0.03 — B200 pulls ahead by 50%.
B200: $0.04 per million tokens. MI355X: $0.05. Both at 385 tok/s/user on MiniMax M3.1 Flash 428B, with B200 15% cheaper. (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): B200 $1.73/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 | B200:$0.008MI355X:$0.017 | B200:$0.019MI355X:$0.029 | B200:$0.042MI355X:$0.048 |
| Concurrency | B200:~32MI355X:~15 | B200:~14MI355X:~7 | B200:~6MI355X:~4 |
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.