Kimi-K2
By
Kimi K2-Instruct-0905 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.
Key Features:
- Large-Scale Training: Pre-trained a 1T parameter MoE model on 15.5T tokens with zero training instability.
- MuonClip Optimizer: We apply the Muon optimizer to an unprecedented scale, and develop novel optimization techniques to resolve instabilities while scaling up.
- Agentic Intelligence: Specifically designed for tool use, reasoning, and autonomous problem-solving.
Technical Specifications
File Support: Attachments not supported
Context window: 256k tokens
Powered by a server managed by @novitaai. Learn more
Build with Kimi-K2 using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from Novita AI
Gemma-4-26B-A4B
Gemma-4-31B-N
MiniMax-Speech-2.8
MiMo-V2-Flash
Minimax-M2.7
Qwen3.5-397B-A17B
Minimax-M2.5
GLM-5
Qwen3-Coder-Next
Kimi-K2.5