Kimi K2 Thinking

State-of-the-art thinking agent with deep reasoning and tool orchestration

Try Now

read docs

About model

Kimi K2 Thinking is Moonshot AI's most capable open-source thinking model, built as a thinking agent that reasons step-by-step while dynamically invoking tools. Setting new state-of-the-art records on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks, K2 Thinking dramatically scales multi-step reasoning depth while maintaining stable tool-use across 200–300 sequential calls — a breakthrough in long-horizon agency with native INT4 quantization for 2x inference speed.

Humanity's Last Exam (w/ tools)

44.9%

Expert-level reasoning across 100+ subjects

Sequential Tool Calls

300

Stable long-horizon agency without drift

Inference Speed-Up

Native INT4 quantization with QAT

Model key capabilities

Deep Thinking & Tool Orchestration: End-to-end trained to interleave chain-of-thought reasoning with function calls for autonomous workflows
Agentic Search Excellence: 60.2% BrowseComp, 56.3% Seal-0 — superior goal-directed web reasoning in information-rich environments
Advanced Mathematical Reasoning: 99.1% AIME 2025 (w/ python), 95.1% HMMT 2025 — elite competition-level problem solving
Production-Ready Efficiency: Native INT4 quantization achieving lossless 2x speed improvements with 256K context window

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 Thinking	84.2%
Related open-source models
Competitor closed-source models
Claude Opus 4.6	90.5%	34.2%			78.7%
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%

API usage

cURL
Python
Typescript

Endpoint:

moonshotai/Kimi-K2-Thinking

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-Thinking",
    "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-Thinking",
  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-Thinking',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

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

Model card
Architecture Overview:
• Mixture-of-Experts (MoE) architecture with 1T total parameters and 32B activated parameters
• 61 total layers including 1 dense layer with 384 experts selecting 8 per token
• Multi-head Latent Attention (MLA) mechanism with 7168 attention hidden dimension
• Native INT4 quantization applied to MoE components through Quantization-Aware Training (QAT)
• 256K context window enabling complex long-horizon agentic tasks
• 160K vocabulary size with SwiGLU activation function

Training Methodology:
• End-to-end trained to interleave chain-of-thought reasoning with function calls
• Quantization-Aware Training (QAT) employed in post-training stage for lossless INT4 inference
• Specialized training for stable long-horizon agency across 200-300 consecutive tool invocations
• Advanced reasoning depth scaling through multi-step test-time computation
• Tool orchestration training enabling autonomous research, coding, and writing workflows

Performance Characteristics:
• State-of-the-art 44.9% on Humanity's Last Exam (HLE) with tools across 100+ expert subjects
• Leading agentic search performance: 60.2% BrowseComp, 62.3% BrowseComp-ZH, 56.3% Seal-0
• Elite mathematical reasoning: 99.1% AIME 2025 (w/ python), 95.1% HMMT 2025 (w/ python), 78.6% IMO-AnswerBench
• Strong coding capabilities: 71.3% SWE-Bench Verified, 61.1% SWE-Bench Multilingual, 83.1% LiveCodeBench v6
• 2x generation speed improvement through native INT4 quantization without performance degradation
• Maintains coherent goal-directed behavior surpassing prior models that degrade after 30-50 steps
‍
Applications & use cases
Agentic Reasoning & Problem Solving:
• Expert-level reasoning across 100+ subjects achieving 44.9% on Humanity's Last Exam with tools
• PhD-level mathematical problem solving through 23+ interleaved reasoning and tool calls
• Elite competition mathematics: 99.1% AIME 2025, 95.1% HMMT 2025 with Python tools
• Dynamic hypothesis generation, evidence verification, and coherent answer construction

Agentic Search & Web Reasoning:
• State-of-the-art 60.2% BrowseComp performance, significantly outperforming 29.2% human baseline
• Continuous browsing, searching, and reasoning over hard-to-find real-world web information
• 200-300 sequential tool calls for deep research workflows without human interference
• Goal-directed web-based reasoning with adaptive hypothesis refinement
• Financial search: 47.4% FinSearchComp-T3, 87.0% Frames benchmark

Agentic Coding & Software Development:
• Production-level coding: 71.3% SWE-Bench Verified, 61.1% SWE-Bench Multilingual, 41.9% Multi-SWE-bench
• Component-heavy frontend development: fully functional HTML, React, and responsive web applications from single prompts
• Multi-step development workflows with precision tool invocation and adaptive reasoning
• Terminal automation: 47.1% Terminal-Bench with simulated tools
• Competitive programming: 83.1% LiveCodeBench v6, 48.7% OJ-Bench (C++)

Creative & Practical Writing:
• Creative writing with vivid imagery, emotional depth, and thematic resonance
• Fiction, cultural reviews, and science fiction with natural fluency and style command
• Academic and research writing with rigorous logic, thoroughness, and substantive richness
• 73.8% Longform Writing benchmark demonstrating instruction adherence and perspective breadth
• Personal and emotional responses with empathy, nuance, and actionable guidance

Long-Horizon Autonomous Workflows:
• Research automation executing hundreds of coherent reasoning steps
• Office automation and document generation workflows
• Multi-step coding projects from ideation to functional products
• Complex problem decomposition into clear, actionable subtasks
• Stable agency surpassing models that degrade after 30-50 steps
‍

Related models

Model specifications

Model data

Model provider
Moonshot AI
Type
Chat
Code
LLM
Main use cases
Chat
Reasoning
Function Calling
Features
Function Calling
Fine tuning
Supported
Deployment
Serverless
On-Demand Dedicated
Monthly Reserved
Endpoint
moonshotai/Kimi-K2-Thinking
Parameters
1T
Activated parameters
32B
Context length
256K
Input price
$1.20 / 1M tokens
Output price
$4.00 / 1M tokens
Input modalities
Text
Output modalities
Text

Released
November 4, 2025
Last updated
November 9, 2025
Quantization level
INT4
External link
Provider docs
Category
Chat

Run in Playground

Quickstart docs

Deploy model

Kimi K2 Thinking

About model

API usage

Model card

Applications & use cases