① アカウント作成 & APIキー発行

アカウント登録 → 電話番号認証 → ダッシュボード →「APIキー」→「+ 新規作成」

② Python (openai SDK)

from openai import OpenAI

client = OpenAI(
    api_key="ly-xxxxxxxxxxxxxxxxxxxx",  # Lykuro APIキー
    base_url="https://api.lykuro.ai/v1",
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",   # provider/model_id 形式
    messages=[{"role": "user", "content": "こんにちは！"}],
)
print(response.choices[0].message.content)

③ Node.js (openai SDK)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "ly-xxxxxxxxxxxxxxxxxxxx",
  baseURL: "https://api.lykuro.ai/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek/deepseek-v4-flash",   // provider/model_id 形式
  messages: [{ role: "user", content: "こんにちは！" }],
});
console.log(response.choices[0].message.content);

④ curl

curl https://api.lykuro.ai/v1/chat/completions \
  -H "Authorization: Bearer ly-xxxxxxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "messages": [{"role": "user", "content": "こんにちは！"}]
  }'

チャット形式での推論リクエスト。OpenAI Chat Completions API と完全互換です。

リクエストボディ

レスポンス例

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "deepseek-v4-flash",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "こんにちは！何かお手伝いできることはありますか？"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 25,
    "total_tokens": 37
  }
}

利用可能なモデル一覧を返します。

curl https://api.lykuro.ai/v1/models \
  -H "Authorization: Bearer ly-xxxxxxxxxxxxxxxxxxxx"