Kimi K2.5/K2.6/K2.7-Code 1T — B300 vs H200 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H200 (NVIDIA Hopper) on Kimi K2.5/K2.6/K2.7-Code 1T. Owning-hyperscaler TCO normalized by output 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.
B300 edges H200 at 40 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T — $0.29 per million tokens versus $0.39, a 36% cost-per-token gap.
Push Kimi K2.5/K2.6/K2.7-Code 1T to 58 tok/s/user and B300 lands at $0.40 per million tokens against H200's $0.48 — B300 pulls ahead by 22%.
B300: $0.54 per million tokens. H200: $0.62. Both at 75 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, with B300 16% cheaper. (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): B300 $2.26/chip/hr · H200 $1.22/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.288H200:$0.391 | B300:$0.399H200:$0.484 | B300:$0.535H200:$0.619 |
| Concurrency | B300:~24H200:~20 | B300:~12H200:~11 | B300:~7H200:~7 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Cost per Million Total Tokens (Owning - Hyperscaler) vs. Interactivity
Kimi K2.5/2.6/2.7-Code 1T • 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