Kimi K2 Instruct
Developed by Moonshot AI, Kimi K 2 Instruct is a chat model that excels at general-purpose conversation and agentic experiences, leveraging its mixture-of-experts (MoE) architecture with 32 billion activated parameters. Notably, it has a large context window of 131,072 tokens, allowing it to process and respond to extensive inputs.
Input
Output
Context
131K
Max Output
2K
Parameters
1026.4B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens2,000 tokens
Parameters1026.4B
Release DateJul 11, 2025
Training CutoffDec 31, 2024
Licenseother
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
More Models by Moonshot AI
Kimi Linear 48B A3B Base1000K context · 49.1B · Open weightsKimi K2.6262K context · 1026.9B · Open weightsMoonlight 16B A3B Instruct8K context · 16B · Open weightsKimi K2.7 Code262K context · 1026.9B · Open weightsKimi K2 Thinking262K context · 1026.4B · Open weightsKimi Dev 72B131K context · 72.7B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.