moonshotai/kimi-k2-thinking
Tanggal rilis: 2025-11-06
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
Coba model
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
| Specification | Value |
|---|---|
| Provider | Moonshotai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 262144 tokens |
| Max Output | 65535 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.4 |
| Output | $1.9 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- 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
Fitur yang Didukung
Panduan Akses API
Kimi K2 Thinking API
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
Konteks
262K
Output Maks.
66K
Penggunaan Tool
Didukung
Coba Kimi K2 Thinking di WaveSpeedAI
Akses Kimi K2 Thinking melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Pertanyaan Umum tentang Kimi K2 Thinking
Berapa biaya Kimi K2 Thinking melalui API?+
Harga di WaveSpeedAI: $0.60 per juta token input dan $2.50 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Berapa context window Kimi K2 Thinking?+
Kimi K2 Thinking mendukung hingga 262K token konteks dengan hingga 66K token output per permintaan.
Apakah Kimi K2 Thinking kompatibel dengan OpenAI?+
Ya. WaveSpeedAI menyediakan Kimi K2 Thinking melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Bagaimana memulai dengan Kimi K2 Thinking?+
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Kimi K2 Thinking.