> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# チャット補完

> TypeScript SDKで/chat/completionsを呼び出します。

**メソッド**: `client.generateText()` (パース済みチャンクをストリーミングするには `client.streamChat()`).

### 例

```typescript theme={null}
const chat = await client.generateText({
  model: "openai/gpt-4o-mini",
  messages: [
    { role: "system", content: "You are helpful." },
    { role: "user", content: "Write a limerick about lighthouses." },
  ],
  temperature: 0.5,
});
```

### ストリーミング

```typescript theme={null}
for await (const chunk of client.streamChat({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Stream a story" }],
})) {
  if (chunk.text) process.stdout.write(chunk.text);
}
```

### 主なパラメーター

* `model` (required): 対象モデルのID。
* `messages` (required): `system|user|assistant|tool`ロールを持つ順序付きメッセージです。コンテンツは文字列または複数のパートで指定します。
* サンプリング： `temperature` (0–2), `top_p` (0–1), `top_k` (>=1), `seed` (int, optional).
* 長さとペナルティ： `max_output_tokens` (int), `presence_penalty` and `frequency_penalty` (-2 to 2), `stop` (string|string\[]).
* ツール： `tools` (定義), `tool_choice` (`auto`/`none`/特定のツール), `max_tool_calls` (int), `parallel_tool_calls` (bool).
* Logprobs： `logprobs` (bool), `top_logprobs` (0–20).
* 出力： `response_format` (json/text), `metadata` (object passthrough), `stream` (bool), `service_tier`.
* Gateway固有の追加項目: `usage`（使用量を要求する真偽値）、`meta`（メタデータブロックを含める真偽値）。

### 戻り値

`ChatCompletionsResponse`

```json theme={null}
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}
```

`stream: true`の場合はSSEフレームが返されます。

```
data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":9,"completion_tokens":12,"total_tokens":21}}

data: [DONE]
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.