moonshotai/Kimi-K2-Instruct

LLM

Kimi-K2 Instruct API by Moonshot

moonshotai/Kimi-K2-Instruct

Kimi-K2-Instruct

Kimi's latest and most powerful open-source model.

パラメータ

コード例
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.getenv("ATLASCLOUD_API_KEY"),
    base_url="https://api.atlascloud.ai/v1"
)

response = client.chat.completions.create(
    model="moonshotai/Kimi-K2-Instruct",
    messages=[
    {
        "role": "user",
        "content": "hello"
    }
],
    max_tokens=1024,
    temperature=0.7
)

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

インストール

お使いの言語に必要なパッケージをインストールしてください。

bash

pip install requests

認証

すべての API リクエストには API キーによる認証が必要です。API キーは Atlas Cloud ダッシュボードから取得できます。

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP ヘッダー

python

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

API キーを安全に保管してください

API キーをクライアントサイドのコードや公開リポジトリに公開しないでください。代わりに環境変数またはバックエンドプロキシを使用してください。

リクエストを送信

import requests

url = "https://api.atlascloud.ai/v1/chat/completions"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1024
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

入力 Schema

以下のパラメータがリクエストボディで使用できます。

合計: 9必須: 2任意: 7

modelstringrequired

The model ID to use for the completion.

Example: "moonshotai/Kimi-K2-Instruct"

messagesarray[object]required

A list of messages comprising the conversation so far.

rolestringrequired

The role of the message author. One of "system", "user", or "assistant".

systemuserassistant

contentstringrequired

The content of the message.

max_tokensinteger

The maximum number of tokens to generate in the completion.

Default: 1024Min: 1

temperaturenumber

Sampling temperature between 0 and 2. Higher values make output more random, lower values more focused and deterministic.

Default: 0.7Min: 0Max: 2

top_pnumber

Nucleus sampling parameter. The model considers the tokens with top_p probability mass.

Default: 1Min: 0Max: 1

streamboolean

If set to true, partial message deltas will be sent as server-sent events.

Default: false

stoparray[string]

Up to 4 sequences where the API will stop generating further tokens.

frequency_penaltynumber

Penalizes new tokens based on their existing frequency in the text so far. Between -2.0 and 2.0.

Default: 0Min: -2Max: 2

presence_penaltynumber

Penalizes new tokens based on whether they appear in the text so far. Between -2.0 and 2.0.

Default: 0Min: -2Max: 2

リクエストボディの例

json

{
  "model": "moonshotai/Kimi-K2-Instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 1024,
  "temperature": 0.7,
  "stream": false
}

出力 Schema

API は ChatCompletion 互換のレスポンスを返します。

idstringrequired

Unique identifier for the completion.

objectstringrequired

Object type, always "chat.completion".

Default: "chat.completion"

createdintegerrequired

Unix timestamp of when the completion was created.

modelstringrequired

The model used for the completion.

choicesarray[object]required

List of completion choices.

indexintegerrequired

Index of the choice.

messageobjectrequired

The generated message.

finish_reasonstringrequired

The reason generation stopped.

stoplengthcontent_filter

usageobjectrequired

Token usage statistics.

prompt_tokensintegerrequired

Number of tokens in the prompt.

completion_tokensintegerrequired

Number of tokens in the completion.

total_tokensintegerrequired

Total tokens used.

レスポンス例

json

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "model-name",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}

Atlas Cloud Skills

Atlas Cloud Skills は 300 以上の AI モデルを AI コーディングアシスタントに直接統合します。ワンコマンドでインストールし、自然言語で画像・動画生成や LLM との対話が可能です。

対応クライアント

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 対応クライアント

インストール

bash

npx skills add AtlasCloudAI/atlas-cloud-skills

API キーの設定

Atlas Cloud ダッシュボードから API キーを取得し、環境変数として設定してください。

bash

export ATLASCLOUD_API_KEY="your-api-key-here"

機能

インストール後、AI アシスタントで自然言語を使用してすべての Atlas Cloud モデルにアクセスできます。

画像生成Nano Banana 2、Z-Image などのモデルで画像を生成します。

動画作成Kling、Vidu、Veo などでテキストや画像から動画を作成します。

LLM チャットQwen、DeepSeek などの大規模言語モデルと対話します。

メディアアップロード画像編集や画像から動画へのワークフロー用にローカルファイルをアップロードします。

詳細を見る

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server は Model Context Protocol を通じて IDE と 300 以上の AI モデルを接続します。MCP 対応のあらゆるクライアントで動作します。

対応クライアント

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 対応クライアント

インストール

bash

npx -y atlascloud-mcp

設定

以下の設定を IDE の MCP 設定ファイルに追加してください。

json

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

利用可能なツール

atlas_generate_imageテキストプロンプトから画像を生成します。

atlas_generate_videoテキストや画像から動画を作成します。

atlas_chat大規模言語モデルと対話します。

atlas_list_models300 以上の利用可能な AI モデルを閲覧します。

atlas_quick_generateモデル自動選択によるワンステップコンテンツ作成。

atlas_upload_mediaAPI ワークフロー用にローカルファイルをアップロードします。

詳細を見る

github.com/AtlasCloudAI/mcp-server

Kimi-K2-Instruct

1. Model Introduction

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being meticulously optimized for agentic capabilities.

Key Features

Large-Scale Training: Pre-trained a 1T parameter MoE model on 15.5T tokens with zero training instability.
MuonClip Optimizer: We apply the Muon optimizer to an unprecedented scale, and develop novel optimization techniques to resolve instabilities while scaling up.
Agentic Intelligence: Specifically designed for tool use, reasoning, and autonomous problem-solving.

Model Variants

Kimi-K2-Base: The foundation model, a strong start for researchers and builders who want full control for fine-tuning and custom solutions.
Kimi-K2-Instruct: The post-trained model best for drop-in, general-purpose chat and agentic experiences. It is a reflex-grade model without long thinking.

2. Model Summary


Architecture	Mixture-of-Experts (MoE)
Total Parameters	1T
Activated Parameters	32B
Number of Layers (Dense layer included)	61
Number of Dense Layers	1
Attention Hidden Dimension	7168
MoE Hidden Dimension (per Expert)	2048
Number of Attention Heads	64
Number of Experts	384
Selected Experts per Token	8
Number of Shared Experts	1
Vocabulary Size	160K
Context Length	128K
Attention Mechanism	MLA
Activation Function	SwiGLU

3. Evaluation Results

Instruction model evaluation results

Benchmark	Metric	Kimi K2 Instruct	DeepSeek-V3-0324	Qwen3-235B-A22B (non-thinking)	Claude Sonnet 4 (w/o extended thinking)	Claude Opus 4 (w/o extended thinking)	GPT-4.1	Gemini 2.5 Flash Preview (05-20)
Coding Tasks
LiveCodeBench v6 (Aug 24 - May 25)	Pass@1	53.7	46.9	37.0	48.5	47.4	44.7	44.7
OJBench	Pass@1	27.1	24.0	11.3	15.3	19.6	19.5	19.5
MultiPL-E	Pass@1	85.7	83.1	78.2	88.6	89.6	86.7	85.6
SWE-bench Verified (Agentless Coding)	Single Patch w/o Test (Acc)	51.8	36.6	39.4	50.2	53.0	40.8	32.6
SWE-bench Verified (Agentic Coding)	Single Attempt (Acc)	65.8	38.8	34.4	72.7*	72.5*	54.6	—
Multiple Attempts (Acc)	71.6	—	—	80.2	79.4*	—	—
SWE-bench Multilingual (Agentic Coding)	Single Attempt (Acc)	47.3	25.8	20.9	51.0	—	31.5	—
TerminalBench	Inhouse Framework (Acc)	30.0	—	—	35.5	43.2	8.3	—
Terminus (Acc)	25.0	16.3	6.6	—	—	30.3	16.8
Aider-Polyglot	Acc	60.0	55.1	61.8	56.4	70.7	52.4	44.0
Tool Use Tasks
Tau2 retail	Avg@4	70.6	69.1	57.0	75.0	81.8	74.8	64.3
Tau2 airline	Avg@4	56.5	39.0	26.5	55.5	60.0	54.5	42.5
Tau2 telecom	Avg@4	65.8	32.5	22.1	45.2	57.0	38.6	16.9
AceBench	Acc	76.5	72.7	70.5	76.2	75.6	80.1	74.5
Math & STEM Tasks
AIME 2024	Avg@64	69.6	59.4*	40.1*	43.4	48.2	46.5	61.3
AIME 2025	Avg@64	49.5	46.7	24.7*	33.1*	33.9*	37.0	46.6
MATH-500	Acc	97.4	94.0*	91.2*	94.0	94.4	92.4	95.4
HMMT 2025	Avg@32	38.8	27.5	11.9	15.9	15.9	19.4	34.7
CNMO 2024	Avg@16	74.3	74.7	48.6	60.4	57.6	56.6	75.0
PolyMath-en	Avg@4	65.1	59.5	51.9	52.8	49.8	54.0	49.9
ZebraLogic	Acc	89.0	84.0	37.7*	73.7	59.3	58.5	57.9
AutoLogi	Acc	89.5	88.9	83.3	89.8	86.1	88.2	84.1
GPQA-Diamond	Avg@8	75.1	68.4*	62.9*	70.0*	74.9*	66.3	68.2
SuperGPQA	Acc	57.2	53.7	50.2	55.7	56.5	50.8	49.6
Humanity's Last Exam (Text Only)	-	4.7	5.2	5.7	5.8	7.1	3.7	5.6
General Tasks
MMLU	EM	89.5	89.4	87.0	91.5	92.9	90.4	90.1
MMLU-Redux	EM	92.7	90.5	89.2	93.6	94.2	92.4	90.6
MMLU-Pro	EM	81.1	81.2*	77.3	83.7	86.6	81.8	79.4
IFEval	Prompt Strict	89.8	81.1	83.2*	87.6	87.4	88.0	84.3
Multi-Challenge	Acc	54.1	31.4	34.0	46.8	49.0	36.4	39.5
SimpleQA	Correct	31.0	27.7	13.2	15.9	22.8	42.3	23.3
Livebench	Pass@1	76.4	72.4	67.6	74.8	74.6	69.8	67.8

• Bold denotes global SOTA, and underlined denotes open-source SOTA.

• Data points marked with * are taken directly from the model's tech report or blog.

• All metrics, except for SWE-bench Verified (Agentless), are evaluated with an 8k output token length. SWE-bench Verified (Agentless) is limited to a 16k output token length.

• Kimi K2 achieves 65.8% pass@1 on the SWE-bench Verified tests with bash/editor tools (single-attempt patches, no test-time compute). It also achieves a 47.3% pass@1 on the SWE-bench Multilingual tests under the same conditions. Additionally, we report results on SWE-bench Verified tests (71.6%) that leverage parallel test-time compute by sampling multiple sequences and selecting the single best via an internal scoring model.

• To ensure the stability of the evaluation, we employed avg@k on the AIME, HMMT, CNMO, PolyMath-en, GPQA-Diamond, EvalPlus, Tau2.

• Some data points have been omitted due to prohibitively expensive evaluation costs.

Base model evaluation results

Benchmark	Metric	Shot	Kimi K2 Base	Deepseek-V3-Base	Qwen2.5-72B	Llama 4 Maverick
General Tasks
MMLU	EM	5-shot	87.8	87.1	86.1	84.9
MMLU-pro	EM	5-shot	69.2	60.6	62.8	63.5
MMLU-redux-2.0	EM	5-shot	90.2	89.5	87.8	88.2
SimpleQA	Correct	5-shot	35.3	26.5	10.3	23.7
TriviaQA	EM	5-shot	85.1	84.1	76.0	79.3
GPQA-Diamond	Avg@8	5-shot	48.1	50.5	40.8	49.4
SuperGPQA	EM	5-shot	44.7	39.2	34.2	38.8
Coding Tasks
LiveCodeBench v6	Pass@1	1-shot	26.3	22.9	21.1	25.1
EvalPlus	Pass@1	-	80.3	65.6	66.0	65.5
Mathematics Tasks
MATH	EM	4-shot	70.2	60.1	61.0	63.0
GSM8k	EM	8-shot	92.1	91.7	90.4	86.3
Chinese Tasks
C-Eval	EM	5-shot	92.5	90.0	90.9	80.9
CSimpleQA	Correct	5-shot	77.6	72.1	50.5	53.5

類似モデルを探索

NEW

HOT

Kimi K2.6 is an advanced large language model with strong reasoning and upgraded native multimodality. It natively understands and processes text and images, delivering more accurate analysis, better instruction following, and stable performance across complex tasks. Designed for production use, Kimi K2.6 is ideal for AI assistants, enterprise applications, and multimodal workflows that require reliable and high-quality outputs.

LLM

Kimi K2.6

Kimi K2.5 is an advanced large language model with strong reasoning and upgraded native multimodality. It natively understands and processes text and images, delivering more accurate analysis, better instruction following, and stable performance across complex tasks. Designed for production use, Kimi K2.5 is ideal for AI assistants, enterprise applications, and multimodal workflows that require reliable and high-quality outputs.

LLM