MoonshotAI: Kimi K2.7 Code

Kimi K2.7 Code is a text-and-image model from MoonshotAI with a 262,144-token context window that matches its maximum completion length, meaning long documents and extended outputs fit within a single session. It supports tool use and reasoning, making it suitable for agentic workflows and multi-step code tasks. Structured output support is unconfirmed, so developers who depend on guaranteed JSON schemas should verify behavior before committing. At $0.75 per million input tokens and $3.50 per million output tokens, the pricing sits in a mid-range tier worth comparing against similarly priced alternatives. The caveat is that no independent benchmark coverage exists yet, so performance claims rest entirely on the vendor. Teams doing code-heavy work who want a long-context model with tool and reasoning support may find it worth trialing, but those who require validated benchmark comparisons before adoption should wait for third-party evaluations.