Model overview
At $0.95 per million input tokens and $4 output, this is the cheapest way into the K2.7 generation and a sensible default until something specific argues otherwise. The 262,144-token window covers most single-repository work; only the flagship reaches further, and it charges $3 input and $15 output for that reach. Cache hits bill $0.19, exactly a fifth of the miss rate, which rewards holding a system prompt and file set stable across an agent loop. The high-speed listing serves the same model at exactly double every figure. Against the general-purpose K2.6 sibling the headline rates are identical, so the distinction is the coding and agent-task framing, not the invoice.
Billing conditions: Standard Kimi API price. Cache-miss input is shown as Input; automatic cache-hit input is shown as Cached input.
- Context window
- 262,144 tokens
- Knowledge cutoff
- —
- Price last verified
- First observed
Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.