Developed by Moonshot AI, Kimi K 2 Instruct 0905 is a state-of-the-art mixture-of-experts (MoE) language model that excels in coding intelligence tasks, demonstrating significant improvements in performance on public benchmarks and real-world coding agent tasks. Notably, it features an extended context length of 262,144 tokens, allowing for better support of long-horizon tasks.
Input
Output
Context
262K
Max Output
262K
Parameters
1026.5B
Input Modalities
Output Modalities
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.