PROVIDER
Moonshot AI AI 模型
Moonshot AI's Kimi K2 — 1T-parameter MoE with 256K context and 58.6% SWE-bench Pro, via one RunAPI key.
1 models
·
2 variants
·
由 $0.020
Moonshot AI 的所有模型
1 models
OVERVIEW
Moonshot AI builds the Kimi K2 family — 1 trillion total parameters, 32B active per token, 384 experts per layer — optimized for autonomous coding and multi-agent orchestration. kimi-k2.6 reaches 58.6% on SWE-bench Pro and scales Agent Swarm to 300 sub-agents. Both kimi-k2.5 and kimi-k2.6 are available through RunAPI from the OpenAI and Anthropic SDKs.
- 單一 API key 可跨 provider 共用
- Model skill 將文件與 schema 帶入你的 workspace
- 按次收費，無需承諾
- 失敗的生成不會收費
FEATURES
亮點
MODELS
Moonshot AI 的所有模型
QUICKSTART
安裝 Moonshot AI model skill。
選一個模型並加入其 skill，讓 coding tool 取得文件、schema、價格備註與 setup 步驟。
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k2.6",
"messages": [
{
"role": "user",
"content": "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass."
}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="kimi-k2.6",
messages=[{"role": "user", "content": "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass."}]
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "kimi-k2.6",
messages: [{ role: "user", content: "Plan and implement a small CLI tool: scaffold the project, write the commands, add tests, and run them until they pass." }]
});REFERENCE
Moonshot AI 的所有變體
FAQ
關於 Moonshot AI 的常見問題
這是 Moonshot AI 的官方整合嗎？
RunAPI 提供託管 API 介面，價格、能力及錯誤行為都清晰透明。
我需要 Moonshot AI 帳戶嗎？
不用 — 你的 RunAPI 密鑰已足夠使用託管存取。
透過 proxy 會增加多少延遲？
通常少於 20 ms。RunAPI 會將 proxy 層維持在貼近 model 執行區域的位置。
圖片／影片會快取嗎？
生成結果會按 task ID 儲存並可供取回。輸入內容不會快取。
我可以使用自己的 key 嗎？
目前不支援 — 請使用 RunAPI 管理的存取。
立即開始