moonshotai/kimi-k2
131,072 context · $0.57/M input tokens · $2.30/M output tokens
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
按用量付費
無需預付費用,僅按實際使用量付費
使用以下程式碼範例整合我們的 API:
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",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 bill
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), reasoning (ZebraLogic, GPQA), and tool-use (Tau2, AceBench) tasks. It supports long-context inference up to 128K tokens and is designed with a novel training stack that includes the MuonClip optimizer for stable large-scale MoE training.
| Specification | Value |
|---|---|
| Provider | Moonshotai |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 131072 tokens |
| Max Output | tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.5 |
| Output | $2.6 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: moonshotai/kimi-k2
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",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "moonshotai/kimi-k2",
"messages": [{"role": "user", "content": "Hello!"}]
}'
moonshotai/kimi-k2
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
輸入
$0.57 /M
輸出
$2.3 /M
上下文
131K
最大輸出
131K
工具調用
支援
WaveSpeedAI 定價:輸入每百萬 token $0.57,輸出每百萬 token $2.30。Prompt 快取與批次處理分別計費,可顯著降低長上下文、高重複任務的實際成本。
Kimi K2 每次請求最多支援 131K 上下文 token,輸出最多 131K token。
是的。WaveSpeedAI 透過 https://llm.wavespeed.ai/v1 的 OpenAI 相容端點提供 Kimi K2。將官方 OpenAI SDK 的 base URL 指向該位址,使用 WaveSpeedAI 的 API Key 即可,無需其他程式碼變更。
登入 WaveSpeedAI,在 Access Keys 建立 API Key,使用上方顯示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 發送請求。新帳號將獲得免費額度,用於試用 Kimi K2。