DeepSeek V4 Pro 0813 1.6T · Performance per dollar

DeepSeek V4 Pro 0813 1.6T — B200 vs GB200 NVL72 performance per dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus GB200 NVL72 (NVIDIA Blackwell) on DeepSeek V4 Pro 0813 1.6T. 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 113 tok/s/user on DeepSeek V4 Pro 0813 1.6T, B200 costs $0.015 per million tokens; GB200 NVL72 costs $0.017. B200 delivers 13% more tokens per dollar at this operating point.

B200 edges GB200 NVL72 at 171 tok/s/user on DeepSeek V4 Pro 0813 1.6T — $0.038 per million tokens versus $0.041, a 7% lower cost per token.

Push DeepSeek V4 Pro 0813 1.6T to 229 tok/s/user and B200 lands at $0.12 per million tokens against GB200 NVL72's $0.11 — GB200 NVL72 costs 6% less. (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 · GB200 NVL72 $1.86/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

GB200 NVL72 vs B200: full specs & benchmarks across models →

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
B200$0.015GB200 NVL72$0.017
B200$0.038GB200 NVL72$0.041
B200$0.12GB200 NVL72$0.11
Concurrency
B200~95GB200 NVL72~198
B200~19GB200 NVL72~41
B200~4GB200 NVL72~6
DeepSeek V4 Pro 0813 1.6T: B200 versus GB200 NVL72 cost per million tokens at matched interactivity levels
B200 versus GB200 NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗