DeepSeek R1 — B300 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on DeepSeek R1. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
At 73 tok/s/user interactivity on DeepSeek R1, B300 delivers 3748 tok/s/chip at $0.17 per million tokens; GB300 NVL72 delivers 6969 tok/s/chip at $0.09. GB300 NVL72 is 82% cheaper per token; GB300 NVL72 delivers 86% more tok/s/chip at this point.
B300 posts 1016 tok/s/chip for $0.62 per million tokens at 126 tok/s/user on DeepSeek R1; GB300 NVL72 posts 3763 tok/s/chip for $0.17. GB300 NVL72 is 262% cheaper per token; GB300 NVL72 delivers 270% more tok/s/chip.
Throughput at 178 tok/s/user on DeepSeek R1: B300 hits 719 tok/s/chip, GB300 NVL72 hits 545. Per-million costs land at $0.87 and $1.18 respectively. B300 is 35% cheaper per token; B300 delivers 32% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:3747.8GB300 NVL72:6968.6 | B300:1015.7GB300 NVL72:3762.8 | B300:718.9GB300 NVL72:544.7 |
| Cost ($/M tok) | B300:$0.168GB300 NVL72:$0.092 | B300:$0.618GB300 NVL72:$0.171 | B300:$0.873GB300 NVL72:$1.178 |
| tok/s/MW | B300:1972518GB300 NVL72:3287059 | B300:534576GB300 NVL72:1774885 | B300:378384GB300 NVL72:256953 |
| Concurrency | B300:~88GB300 NVL72:~679 | B300:~8GB300 NVL72:~253 | B300:~9GB300 NVL72:~20 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
DeepSeek R1 0528 671B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip