GPT Image 2 is LIVE Now. Try in Image Generator→
moonshot

moonshotai/kimi-k2-thinking

moonshotai/kimi-k2-thinking

262,144 context · $0.60/M input tokens · $2.50/M output tokens

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Harga

Bayar sesuai pemakaian

Tanpa biaya di muka, bayar hanya sesuai penggunaan

Input$0.60 / M Tokens
Output$2.50 / M Tokens

Penggunaan API

Gunakan contoh kode berikut untuk integrasi dengan API kami:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

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

Pengenalan Model

Moonshotai kimi-k2-thinking

moonshotai kimi-k2-thinking


Why It Looks Great

  • Large Language Model architecture for efficient processing
  • 262144 context window for long document handling
  • Competitive pricing at $0.4/$1.9 per million tokens

Key Features

  • Context Window: 262144 tokens
  • Max Output: 65535 tokens
  • Vision: Supported
  • Function Calling: Supported

Specifications

SpecificationValue
ProviderMoonshotai
Model TypeLarge Language Model (LLM)
ArchitectureN/A
Context Window262144 tokens
Max Output65535 tokens
InputText
OutputText
VisionSupported
Function CallingSupported

Pricing

Token TypeCost per Million Tokens
Input$0.4
Output$1.9

How to Use

  1. Write your prompt — describe the task, provide context, and specify desired output format.
  2. Submit — the model processes your request and returns the response.

API Integration

Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: moonshotai/kimi-k2-thinking


API Usage

Python SDK

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://llm.wavespeed.ai/v1"
)

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

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

cURL

curl https://llm.wavespeed.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "moonshotai/kimi-k2-thinking",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Notes

  • Model: moonshotai/kimi-k2-thinking
  • Provider: Moonshotai

Info

Providermoonshot
Typellm

Fitur yang Didukung

Input
Text
Output
Text
Konteks262,144
Output Maks65,535
Vision-
Function Calling✓ Supported

Panduan Akses API

Base URLhttps://llm.wavespeed.ai/v1
API Endpointchat/completions
Model IDmoonshotai/kimi-k2-thinking

moonshotai/kimi-k2-thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

Input

$0.6 /M

Output

$2.5 /M

Context

262K

Max Output

66K

Tool Use

Supported

Try moonshotai/kimi-k2-thinking on WaveSpeedAI

Access moonshotai/kimi-k2-thinking through our unified API — OpenAI-compatible, no cold starts, transparent pricing.

Open Playground