Kimi K2.5/K2.6/K2.7-Code 1T · Performance per Dollar

Kimi K2.5/K2.6/K2.7-Code 1T — B200 vs H200 Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) 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.

Push Kimi K2.5/K2.6/K2.7-Code 1T to 45 tok/s/user and B200 lands at $0.30 per million tokens against H200's $0.41 — B200 costs 27% less.

B200: $0.41 per million tokens. H200: $0.50. Both at 61 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B200 19% cheaper.

Toward the upper edge of the 30–92 tok/s/user interactivity band — at 77 tok/s/user — B200 runs $0.58 per million tokens on Kimi K2.5/K2.6/K2.7-Code 1T while H200 runs $0.64. B200 is the cheaper choice by 9%. (Numbers reflect the default 8k/1k · int4 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 · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.

View full latency and throughput comparison →

B200 vs H200: full specs & benchmarks across models →

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$0.30H200$0.41
B200$0.41H200$0.50
B200$0.58H200$0.64
Concurrency
B200~32H200~17
B200~17H200~10
B200~10H200~6
Kimi K2.5/K2.6/K2.7-Code 1T: B200 versus H200 cost per million tokens at matched interactivity levels
B200 versus H200 cost per million tokens for this comparison's canonical default workload. Lower cost indicates better performance per dollar.
Open full-size image ↗