Kimi K2.6 是 Kimi 最新最智能的模型,具备更强更稳的长程代码编写能力,指令遵循和自我纠错能力显著提升,同时支持文本、图片与视频输入,思考与非思考模式,对话与 Agent 任务 模型上下文长度 256k,支持长思考擅长深度推理 支持自动上下文缓存功能,ToolCalls、JSON Mode、Partial Mode、联网搜索功能等能力
from openai import OpenAI
client = OpenAI(
base_url="https://api.openroute.cn/v1",
api_key="<ONTOROUTE_API_KEY>",
)
completion = client.chat.completions.create(
model="moonshot/kimi-k2.6",
messages=[
{
"role": "user",
"content": "Write a one-sentence bedtime story about a unicorn.",
}
],
)
print(completion.choices[0].message.content)Prices are CNY (¥) per million tokens, billed as you go. Cache reads can cut the cost of repeated context.
| Provider | Input | Output | Cache read | Context length | Latency | Uptime | Status |
|---|---|---|---|---|---|---|---|
moonshot moonshot/kimi-k2.6 | ¥6.50 | ¥27.00 | Supported | 256K | 466ms | 88.70% | Lowest |
This model does not publish tunable parameters.