Kimi K2 0711

About Kimi K2 0711

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.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Moonshot AI Model Lineup

Compare all models from Moonshot AI to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

GLM 5.2 (batch)

Zhipu Ai

Input: $0.70

Output: $2.20

Context: 512k

Qwen3 VL 235B A22B Thinking

Alibaba Qwen

Input: $0.26

Output: $2.60

Context: 131k

Qwen3.5-27B

Alibaba Qwen

Input: $0.26

Output: $2.60

Context: 262k

R1 0528

DeepSeek

Input: $0.57

Output: $2.29

Context: 164k

💡 Cheaper Alternatives

Same Brand (Moonshot AI)

Cross Brand

🚀 Quick Start

Get started with Kimi K2 0711 API

from openai import OpenAI

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

response = client.chat.completions.create(
    model="moonshotai/kimi-k2",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision