AICU API - AI-Driven MVP Development

# AICU LLM API Documentation

> OpenAI互換のチャット補完API - Beta版（認証なしで利用可能）

## Base URL

```
https://api.aicu.ai/v1
```

## Quick Start

```bash
curl -X POST https://api.aicu.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v3",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'
```

---

## POST /v1/chat/completions

OpenAI互換のチャット補完エンドポイント。

**Request:**
```json
{
  "model": "deepseek-v3",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "max_tokens": 1000,
  "temperature": 0.7,
  "stream": false
}
```

**Parameters:**
| Name | Type | Required | Description |
|------|------|----------|-------------|
| model | string | Yes | モデルID |
| messages | array | Yes | メッセージ配列 |
| max_tokens | number | No | 最大トークン数 (default: 4096) |
| temperature | number | No | サンプリング温度 0-2 (default: 1) |
| stream | boolean | No | ストリーミング (default: false) |

**Response:**
```json
{
  "id": "gen-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "deepseek-v3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}
```

**Response Headers:**
- `X-AICU-Model`: 使用モデル
- `X-AICU-Provider`: プロバイダ (openrouter/groq/aicu)
- `X-AICU-Tokens`: 消費トークン数
- `X-AICU-AP-Cost`: AP消費
- `X-AICU-Latency-Ms`: レイテンシ

---

## GET /v1/chat/models

利用可能なモデル一覧を取得。

```bash
curl https://api.aicu.ai/v1/chat/models
```

**Response:**
```json
{
  "object": "list",
  "data": [
    {
      "id": "deepseek-v3",
      "owned_by": "openrouter",
      "pricing": {"ap_per_1k_tokens": 3},
      "stage": "beta",
      "description": "汎用、コスパ良好"
    }
  ]
}
```

---

## Available Models

| Model | Provider | Cost | Description |
|-------|----------|------|-------------|
| groq-llama-3.3-70b | Groq | 0 AP (free) | 高品質、30 RPM制限 |
| groq-llama-3.1-8b | Groq | 0 AP (free) | 高速、30 RPM制限 |
| deepseek-v3 | OpenRouter | 3 AP/1K | 汎用、コスパ良好 |
| gemini-flash | OpenRouter | 5 AP/1K | マルチモーダル |
| llama-3.1-8b | OpenRouter | 2 AP/1K | 軽量 |
| llama-3.1-70b | OpenRouter | 20 AP/1K | 高品質 |
| qwen3-32b | OpenRouter | 10 AP/1K | 大規模コンテキスト |

---

## OpenAI SDK Compatibility

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aicu.ai/v1",
    api_key="dummy"  # Beta: 認証不要
)

response = client.chat.completions.create(
    model="deepseek-v3",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
```

```typescript
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.aicu.ai/v1',
  apiKey: 'dummy',
});

const response = await client.chat.completions.create({
  model: 'deepseek-v3',
  messages: [{ role: 'user', content: 'Hello!' }],
});
```

---

## Credits (課金)

- 100 AP = ¥1
- Groqモデル: 無料（レート制限あり）
- Beta版: 認証なしで利用可能

---

## Rate Limits

| Provider | Limit |
|----------|-------|
| Groq | 30 RPM |
| OpenRouter | プランに依存 |

---

## Support

- Skill: https://api.aicu.ai/skills/llm
- Dashboard: https://api.aicu.ai/dashboard
- Contact: https://corp.aicu.ai/ja/contact

© 2026 AICU Japan K.K.
Documentation

AIエージェント向け SKILLS.md

Interactive API Reference
