Kimi K2.5/K2.6/K2.7-Code 1T · Performance per Dollar
Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs B300 Performance per Dollar
Cost per million tokens of B200 (NVIDIA Blackwell) versus B300 (NVIDIA Blackwell) on Kimi K2.5/K2.6/K2.7-Code 1T. 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.
B200: $0.059 per million tokens. B300: $0.18. Both at 50 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B200 67% cheaper.
Around the middle of the 9–173 tok/s/user interactivity band — at 91 tok/s/user — B200 runs $0.28 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while B300 runs $0.32. B200 is the cheaper choice by 14%.
On Kimi K2.5/K2.6/K2.7-Code 1T at 132 tok/s/user, the per-million math comes out to $0.50 for B200 and $0.73 for B300; B200 delivers 47% more total tokens per dollar. (Numbers reflect the default 8k/1k · 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 · B300 $2.26/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
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$0.059B300$0.18 | B200$0.28B300$0.32 | B200$0.50B300$0.73 |
| Concurrency | B200~323B300~32 | B200~62B300~10 | B200~30B300~3 |
