DeepSeek V4.1 Flash 552B — B200 vs MI300X Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus MI300X (AMD CDNA 3) on DeepSeek V4.1 Flash 552B. 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 →
At 61 tok/s/user on DeepSeek V4.1 Flash 552B, B200 costs $0.01 per million tokens; MI300X costs $0.04. B200 is 720% more cost-efficient at this operating point.
B200 edges MI300X at 104 tok/s/user on DeepSeek V4.1 Flash 552B — $0.01 per million tokens versus $0.06, a 827% cost-per-token gap.
Push DeepSeek V4.1 Flash 552B to 147 tok/s/user and B200 lands at $0.01 per million tokens against MI300X's $0.12 — B200 pulls ahead by 1158%. (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 · MI300X $0.95/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:$0.005MI300X:$0.043 | B200:$0.007MI300X:$0.065 | B200:$0.010MI300X:$0.124 |
| Concurrency | B200:~64MI300X:~10 | B200:~41MI300X:~5 | B200:~26MI300X:~2 |
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.