Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
Input
Output
Context
131K
Max Output
131K
Parameters
—
Input Modalities
Output Modalities
Input
$0.570
Output
$2.30
| Platform | Input | Output |
|---|---|---|
OpenRouter | $0.570 | $2.30 |
Data sourced from official provider APIs and documentation
Last updated: Mar 24, 2026
Explore models, compare pricing and benchmarks, and right-size your infrastructure — all in one place.