Kimi K3 Is Live
Kimi Code has released the K3 model, which is now available alongside the K2.7 Code model. The update includes specific instructions for switching models and managing context cache to optimize performance and costs.
Why it matters
Frequent model updates in the AI space require users to understand technical trade-offs regarding context caching and API efficiency.
This page covers the models Kimi Code provides and how to switch between them in each client.
Kimi Code currently offers two models—Kimi K3 and Kimi K2.7 Code—across three model IDs, selectable by model ID in clients or third-party tools. Model specs:
Different membership plans unlock different models, context windows, and speeds. Upgrade your plan →
After switching models, the context cache built earlier no longer hits on the new model, so that context has to be re-prefilled. Usage therefore looks higher right after switching. Recommended action:
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in