DeepSeek V4 Pro 1.6T · Performance per Dollar

DeepSeek V4 Pro 1.6T — GB300 NVL72 vs H200 Performance per Dollar

Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on DeepSeek V4 Pro 1.6T. Owning-hyperscaler TCO normalized by output 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.

H200 costs $1.85 per million tokens at 45 tok/s/user on DeepSeek V4 Pro 1.6T; we have no GB300 NVL72 benchmark data at this exact target.

At 87 tok/s/user on DeepSeek V4 Pro 1.6T, H200 comes in at $4.26 per million tokens. GB300 NVL72 hasn't been benchmarked at this operating point.

Only H200 has cost data at 128 tok/s/user on DeepSeek V4 Pro 1.6T — $6.36 per million tokens. GB300 NVL72 is unmeasured at this target. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

GPU pricing (owning hyperscaler): GB300 NVL72 $2.65/GPU/hr · H200 $1.41/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + 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)
Dollar per Million Tokens
GB300 NVL72:H200:$1.851
GB300 NVL72:H200:$4.262
GB300 NVL72:H200:$6.362
Concurrency
GB300 NVL72:H200:~20
GB300 NVL72:H200:~5
GB300 NVL72:H200:~2

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.