The Moonshot AI Kimi K2.8 Preview model has been fully launched for Kimi Code; the Model ID remains kimi-for-coding, and no configuration changes are required for clients or third-party tools. According to the official announcement, the model’s overall performance is close to K3, with enhanced coding and agent capabilities, and significantly improved reasoning efficiency compared to K2.7 Code. Kimi K2.8 Preview supports the same thinking effort levels as K3—low, high, and max—with max set as default. All membership tiers now offer a maximum context window of 1M.
Moonshot Kimi K2.8 Preview Model Fully Launched, Performance Approaching K3
TechFlowShare
Summary
The Moonshot Kimi K2.8 Preview model is now fully available on Kimi Code, using the same Model ID: kimi-for-coding. Users can access it directly without adjusting client or third-party tool settings. Performance is nearly on par with K3, offering enhanced coding and agent capabilities compared to K2.7 Code. Thinking efficiency has improved significantly. It supports low, high, and max thinking effort levels, with max set as default. All membership tiers now receive the full 1M context window. This update brings fresh on-chain and crypto news for developers and users.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.