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.
Pricing
Pay-as-you-go rates for this model. More details can be found here.
Input Tokens (1M)
$0.29
Output Tokens (1M)
$1.15
Capabilities
Input Modalities
Text
Output Modalities
Text
Supported Parameters
Available parameters for API requests
Frequency Penalty
Logit Bias
Logprobs
Max Completion Tokens
Parallel Tool Calls
Presence Penalty
Response Format
Stop
Temperature
Tool Choice
Tools
Top P