Kimi K2.5 is Moonshot AI's flagship agentic model and a new SOTA open model. It unifies vision and text, thinking and non-thinking modes, and single-agent and multi-agent execution into one model. Fireworks enables users to control the reasoning behavior of the Kimi K2.5 model and inspect its reasoning history for greater transparency.
Fine-tuningDocs | Kimi K2.5 can be customized with your data to improve responses. Fireworks uses LoRA to efficiently train and deploy your personalized model |
On-demand DeploymentDocs | On-demand deployments allow you to use Kimi K2.5 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits. |
