Kimi-K2 Instruct API by Moonshot
Kimi's latest and most powerful open-source model.
कोड उदाहरण
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)इंस्टॉल करें
अपनी प्रोग्रामिंग भाषा के लिए आवश्यक पैकेज इंस्टॉल करें।
pip install requestsप्रमाणीकरण
सभी API अनुरोधों के लिए API कुंजी के माध्यम से प्रमाणीकरण आवश्यक है। आप अपनी API कुंजी Atlas Cloud डैशबोर्ड से प्राप्त कर सकते हैं।
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP हेडर
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}क्लाइंट-साइड कोड या सार्वजनिक रिपॉज़िटरी में अपनी API कुंजी कभी उजागर न करें। इसके बजाय एनवायरनमेंट वेरिएबल या बैकएंड प्रॉक्सी का उपयोग करें।
अनुरोध सबमिट करें
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())Input Schema
अनुरोध बॉडी में निम्नलिखित पैरामीटर स्वीकार किए जाते हैं।
अनुरोध बॉडी का उदाहरण
{
"model": "moonshotai/Kimi-K2-Instruct",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 1024,
"temperature": 0.7,
"stream": false
}Output Schema
API एक ChatCompletion-संगत प्रतिक्रिया लौटाता है।
प्रतिक्रिया का उदाहरण
{
"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 300+ AI मॉडल को सीधे आपके AI कोडिंग असिस्टेंट में इंटीग्रेट करता है। इंस्टॉल करने के लिए एक कमांड, फिर इमेज, वीडियो जनरेट करने और LLM के साथ चैट करने के लिए प्राकृतिक भाषा का उपयोग करें।
समर्थित क्लाइंट
इंस्टॉल करें
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI कुंजी सेटअप करें
Atlas Cloud डैशबोर्ड से अपनी API कुंजी प्राप्त करें और इसे एनवायरनमेंट वेरिएबल के रूप में सेट करें।
export ATLASCLOUD_API_KEY="your-api-key-here"क्षमताएँ
एक बार इंस्टॉल होने के बाद, आप सभी Atlas Cloud मॉडल तक पहुँचने के लिए अपने AI असिस्टेंट में प्राकृतिक भाषा का उपयोग कर सकते हैं।
MCP Server
Atlas Cloud MCP Server आपके IDE को Model Context Protocol के माध्यम से 300+ AI मॉडल से जोड़ता है। किसी भी MCP-संगत क्लाइंट के साथ काम करता है।
समर्थित क्लाइंट
इंस्टॉल करें
npx -y atlascloud-mcpकॉन्फ़िगरेशन
अपने IDE की MCP सेटिंग्स फ़ाइल में निम्नलिखित कॉन्फ़िगरेशन जोड़ें।
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}उपलब्ध टूल
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 |
