DeepSeek V4.1 Flash 552B — B300 vs GB200 NVL72 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) 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 →
Near the low end of the 26–298 tok/s/user interactivity band — at 94 tok/s/user — B300 runs $0.01 per million tokens on DeepSeek V4.1 Flash 552B while GB200 NVL72 runs $0.01. B300 is the cheaper choice by 7%.
On DeepSeek V4.1 Flash 552B at 162 tok/s/user, the per-million math comes out to $0.02 for B300 and $0.02 for GB200 NVL72; B300 delivers 6% more total tokens per dollar.
At 230 tok/s/user on DeepSeek V4.1 Flash 552B, B300 costs $0.04 per million tokens; GB200 NVL72 costs $0.03. GB200 NVL72 is 3% more cost-efficient 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): B300 $2.26/chip/hr · GB200 NVL72 $1.86/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:$0.010GB200 NVL72:$0.011 | B300:$0.020GB200 NVL72:$0.021 | B300:$0.035GB200 NVL72:$0.034 |
| Concurrency | B300:~36GB200 NVL72:~27 | B300:~18GB200 NVL72:~14 | B300:~10GB200 NVL72:~8 |
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.