DeepSeek V4.1 Flash 552B — B300 vs MI355X Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) 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 →
Cost-per-million is essentially even between B300 ($0.01) and MI355X ($0.01) at 191 tok/s/user on DeepSeek V4.1 Flash 552B.
At 319 tok/s/user on DeepSeek V4.1 Flash 552B, B300 costs $0.02 per million tokens; MI355X costs $0.01. MI355X is 63% more cost-efficient at this operating point.
MI355X edges B300 at 447 tok/s/user on DeepSeek V4.1 Flash 552B — $0.03 per million tokens versus $0.06, a 90% cost-per-token gap. (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:$0.006MI355X:$0.006 | B300:$0.024MI355X:$0.015 | B300:$0.056MI355X:$0.029 |
| Concurrency | B300:~26MI355X:~32 | B300:~14MI355X:~7 | B300:~2MI355X:~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.