Kimi K3.1 Pro Highspeed
Moonshot Kimi 对话模型，适合长文本理解与分析。
Some providers degraded1 providers available
Context128K
Max output32K
$4/ 1M tokensInput price · by access tier0.88折$0.35/ 1M tokens2折$0.8/ 1M tokens4.5折$1.8/ 1M tokens7折$2.8/ 1M tokens$20/ 1M tokensOutput price · by access tier0.88折$1.76/ 1M tokens2折$4/ 1M tokens4.5折$9/ 1M tokens7折$14/ 1M tokensCache read$0.2/1M tokens
Cache write$2/1M tokens
Capabilities
Input modality
InputText
OutputText
Core capabilities
Streaming
Structured outputTool capabilities
Function callingAccess protocols
—
Pricing details
| Tier | Price (input–output) | Cache read | Cache write |
|---|---|---|---|
| ≦200K | $4-$20/1M tokens | $0.2/1M tokens | $2/1M tokens |
Service performance
Success rate47.92%Last 24 hours
First token latency1600msLast 24 hours
Quickstart
from openai import OpenAI
client = OpenAI(
base_url="https://api.apione.ai/v1",
api_key="<YOUR_API_KEY>", # 在控制台创建 API Key 后替换
)
response = client.chat.completions.create(
model="kimi-k3.1-pro-highspeed",
messages=[{"role": "user", "content": "用一句话介绍你自己"}],
)
print(response.choices[0].message.content)