Kimi K2 Instruct (via Groq)
1T Parameter MoE Model with 32B Activated Parameters - Fast Inference
Model Highlights
Exceptional Performance
SOTA on coding (SWE-bench 65.8%), math (AIME 2024 69.6%), and tool use
Agentic Intelligence
Designed for tool use, reasoning, and autonomous problem-solving
MuonClip Optimizer
Trained on 15.5T tokens with zero training instability
Kimi K2 is now available through Groq! Make sure your Groq API key is configured. The model is accessible at 'groq.kimiK2' for fast inference.
Chat with Kimi K2
Experience the power of a 1T parameter model with state-of-the-art capabilities
Start a conversation with Kimi K2
Try asking about coding, math, or complex reasoning tasks!
Try these examples: