Kimi K2 Instruct-0905

State-of-the-art mixture-of-experts agentic intelligence model with 1 T parameters, 256K context, and native tool use

About model

Kimi K2-Instruct-0905 is a state-of-the-art mixture-of-experts language model with 32 billion activated parameters, excelling in agentic coding intelligence and frontend coding experience, suitable for developers and coding tasks.

Quickstart guides

Apps

How to Build a Lovable Clone with Kimi K2

Agents

Agent Workflows

RAG

Building a RAG Workflow

Performance benchmarks

Model	GPQA Diamond	HLE	LiveCodeBench	MATH500	SWE-bench verified
Kimi K2 Instruct-0905					69.2%
Related open-source models
Competitor closed-source models
OpenAI o3	83.3%	24.9%		99.2%	62.3%
OpenAI o1	76.8%			96.4%	48.9%
GPT-4o	49.2%	2.7%	32.3%	89.3%	31.0%
Gemini 2.0 Flash	64.1%		34.5%	93.0%

API usage

cURL
Python
Typescript

Endpoint:

moonshotai/Kimi-K2-Instruct-0905

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/Kimi-K2-Instruct-0905",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'

from together import Together

client = Together()

response = client.chat.completions.create(
  model="moonshotai/Kimi-K2-Instruct-0905",
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)

import Together from 'together-ai';
const together = new Together();

const completion = await together.chat.completions.create({
  model: 'moonshotai/Kimi-K2-Instruct-0905',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

console.log(completion.choices[0].message.content);

How to use model

Get started with this model in 10 lines of code! The model ID is moonshotai/Kimi-K2-Instruct-0905 and the pricing is $1 for input tokens and $3 for output tokens.

    
      from together import Together

      client = Together()
      resp = client.chat.completions.create(
          model="moonshotai/Kimi-K2-Instruct",
          messages=[{"role":"user","content":"Code a hacker news clone"}],
          stream=True,
      )
      for tok in resp:
          print(tok.choices[0].delta.content, end="", flush=True)

Model card
Architecture Overview:
‍‍1 T-parameter MoE with 32 B activated parameters
Hybrid MoE sparsity for compute efficiency
256K token context for deep document comprehension
Agentic design with native tool usage & CLI integration‍
Training Methodology:
‍‍Pre-trained on 15.5 T tokens using MuonClip optimizer for stability
Zero-instability training at large scale
‍Performance Characteristics:‍
SOTA on LiveCodeBench v6, AIME 2025, MMLU-Redux, and SWE-bench (agentic)
Prompting
Use natural language instructions or tool commands
Temperature ≈ 0.6: Calibrated to Kimi‑K2‑Instruct’s RLHF alignment curve; higher values yield verbosity.
Kimi K2 autonomously invokes tools to fulfill tasks: Pass a JSON schema in tools=[…]; set tool_choice="auto". Kimi decides when/what to call.
Supports multi-turn dialogues & chained workflows: Because the model is “agentic”, give a high‑level objective (“Analyse this CSV and write a report”), letting it orchestrate sub‑tasks.
Applications & use cases
Kimi K2 shines in scenarios requiring autonomous problem-solving – specifically with coding & tool use:
Agentic Workflows: Automate multi-step tasks like booking flights, research, or data analysis using tools/APIs
Coding & Debugging: Solve software engineering tasks (e.g., SWE-bench), generate patches, or debug code
Research & Report Generation: Summarize technical documents, analyze trends, or draft reports using long-context capabilities
STEM Problem-Solving: Tackle advanced math (AIME, MATH), logic puzzles (ZebraLogic), or scientific reasoning
Tool Integration: Build AI agents that interact with APIs (e.g., weather data, databases).

Related models

Model specifications

Model data

Model provider
Moonshot AI
Type
LLM
Main use cases
Chat
Function Calling
Features
Function Calling
Speed
Medium
Intelligence
Very High
Deployment
Serverless
Endpoint
moonshotai/Kimi-K2-Instruct-0905
Parameters
1.0T
Context length
262K
Input price
$1.00 / 1M tokens
Output price
$3.00 / 1M tokens
Input modalities
Text
Output modalities
Text

Released
September 2, 2025
Last updated
September 4, 2025
Quantization level
FP8
External link
Provider docs
Category
Chat

Run in Playground

Quickstart docs

Deploy model

Kimi K2 Instruct-0905

About model

API usage

How to use model

Model card

Prompting

Applications & use cases