DeepSeek V4.1 Flash 552B · Performance per dollar

DeepSeek V4.1 Flash 552B — B300 vs Vera Rubin NVL72 performance per dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 →

B300: $0.006 per million tokens. Vera Rubin NVL72: $0.000. Both at 344 tok/s/user on DeepSeek V4.1 Flash 552B, with Vera Rubin NVL72 92% cheaper.

Around the middle of the 181–833 tok/s/user interactivity band — at 507 tok/s/user — B300 runs $0.011 per million tokens on DeepSeek V4.1 Flash 552B while Vera Rubin NVL72 runs $0.001. Vera Rubin NVL72 is the cheaper choice by 93%.

On DeepSeek V4.1 Flash 552B at 670 tok/s/user, the per-million math comes out to $0.025 for B300 and $0.002 for Vera Rubin NVL72; Vera Rubin NVL72 delivers 16× the total tokens per dollar. (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 · Vera Rubin NVL72 $3.61/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.

Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollars per million tokens
B300$0.006Vera Rubin NVL72$0.000
B300$0.011Vera Rubin NVL72$0.001
B300$0.025Vera Rubin NVL72$0.002
Concurrency
B300~45Vera Rubin NVL72~11,236
B300~28Vera Rubin NVL72~8,441
B300~13Vera Rubin NVL72~3,414
DeepSeek V4.1 Flash 552B: B300 versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
B300 versus Vera Rubin NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗