Kimi K2.8 Preview Model Launched, Overall Performance Close to K3

The Kimi K2.8 Preview model has been fully launched on Kimi Code today, with Model ID kimi-for-coding. Clients and third-party tools can use it without modifying configurations. The official statement indicates that the K2.8 Preview's overall performance is close to that of K3, with higher thinking efficiency. Coding and agent capabilities have been comprehensively enhanced, and thinking efficiency has significantly improved compared to K2.7 Code, with all membership tiers now offering a maximum context window of 1M. Kimi K2.8 Preview supports adjustable thinking effort tiers, consistent with K3's thinking levels, offering low/high/max options (default is max). When thinking is disabled, requests for both the K3 series and K2.8 Preview are routed to K2.8 Preview (no thinking).

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.