Muse Spark 1.3/Open 816B · Performance per dollar

Muse Spark 1.3/Open 816B — GB300 NVL72 vs Vera Rubin NVL72 performance per dollar

Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) on Muse Spark 1.3/Open 816B. 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 →

On Muse Spark 1.3/Open 816B at 259 tok/s/user, the per-million math comes out to $0.026 for GB300 NVL72 and $0.016 for Vera Rubin NVL72; Vera Rubin NVL72 delivers 66% more total tokens per dollar.

At 411 tok/s/user on Muse Spark 1.3/Open 816B, GB300 NVL72 costs $0.060 per million tokens; Vera Rubin NVL72 costs $0.024. Vera Rubin NVL72 delivers 148% more tokens per dollar at this operating point.

Vera Rubin NVL72 edges GB300 NVL72 at 562 tok/s/user on Muse Spark 1.3/Open 816B — $0.037 per million tokens versus $0.13, a 72% lower cost per token. (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): GB300 NVL72 $2.31/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
GB300 NVL72$0.026Vera Rubin NVL72$0.016
GB300 NVL72$0.060Vera Rubin NVL72$0.024
GB300 NVL72$0.13Vera Rubin NVL72$0.037
Concurrency
GB300 NVL72~53Vera Rubin NVL72~35
GB300 NVL72~54Vera Rubin NVL72~39
GB300 NVL72~12Vera Rubin NVL72~100
Muse Spark 1.3/Open 816B: GB300 NVL72 versus Vera Rubin NVL72 cost per million tokens at matched interactivity levels
GB300 NVL72 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 ↗