Kimi K3.1 Pro · Performance per Dollar

Kimi K3.1 Pro — B300 vs GB300 NVL72 Performance per Dollar

Cost per million tokens of B300 (NVIDIA Blackwell) versus GB300 NVL72 (NVIDIA Blackwell) on Kimi K3.1 Pro. 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 →

Near the low end of the 62–240 tok/s/user interactivity band — at 106 tok/s/user — B300 runs $0.10 per million tokens on Kimi K3.1 Pro while GB300 NVL72 runs $0.04. GB300 NVL72 is the cheaper choice by 140%.

On Kimi K3.1 Pro at 151 tok/s/user, the per-million math comes out to $0.13 for B300 and $0.07 for GB300 NVL72; GB300 NVL72 delivers 89% more total tokens per dollar.

At 196 tok/s/user on Kimi K3.1 Pro, B300 costs $0.21 per million tokens; GB300 NVL72 costs $0.12. GB300 NVL72 is 73% more cost-efficient at this operating point. (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 · GB300 NVL72 $2.31/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

GB300 NVL72 vs B300: full specs & benchmarks across models →

Kimi K3.1 Pro: B300 versus GB300 NVL72 cost per million tokens at matched interactivity levels — B300 versus GB300 NVL72 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.

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	B300:$0.103GB300 NVL72:$0.043	B300:$0.132GB300 NVL72:$0.070	B300:$0.212GB300 NVL72:$0.122
Concurrency	B300:~13GB300 NVL72:~70	B300:~6GB300 NVL72:~45	B300:~3GB300 NVL72:~30