Kimi K2

kimi-k2
byMoonShotAI|Created Jul 12, 2025
Chat Completions

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

Usage Analytics

Token usage across the last 30 active days

Uptime

Reliability over the last 7 days

Throughput

Time-To-First-Token (TTFT)

Code Example

Example code for using this model through our API with Python (OpenAI SDK) or cURL. Replace placeholders with your API key and model ID.

Basic request example. Ensure API key permissions. For more details, see our documentation.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.naga.ac/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="kimi-k2",
    messages=[
        {{"role": "user", "content": "What's 2+2?"}}
    ],
    temperature=0.2,
)
print(resp.choices[0].message.content)