MoonshotAI Kimi K2

MoonshotAI Kimi K2 on W&B Inference

Price per 1M tokens

$1.35 (input)
$4.00 (output)

Parameters

32B (active)
1T (total)

Context window

128K

Release date

July 2025

Kimi K2 inference details

Kimi K2 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.

Created by: MoonshotAI

License: Other

🤗 model card: Kimi K2 instruct

				
					import openai
import weave

# Weave autopatches OpenAI to log LLM calls to W&B
weave.init("<team>/<project>")

client = openai.OpenAI(
    # The custom base URL points to W&B Inference
    base_url='https://api.inference.wandb.ai/v1',

    # Get your API key from https://wandb.ai/authorize
    # Consider setting it in the environment as OPENAI_API_KEY instead for safety
    api_key="<your-apikey>",

    # Team and project are required for usage tracking
    project="<team>/<project>",
)

response = client.chat.completions.create(
    model="moonshotai/Kimi-K2-Instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me a joke."}
    ],
)

print(response.choices[0].message.content)