> ## 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.

# 聊天补全

> 使用 TypeScript SDK 调用 /chat/completions。

**方法**: `client.generateText()` (使用以下方法流式传输已解析的内容块： `client.streamChat()`).

### 示例

```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,
});
```

### 流式传输

```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);
}
```

### 主要参数

* `model` (required): 目标模型 ID。
* `messages` (required): 按顺序排列的消息，角色为 `system|user|assistant|tool`；内容可以是字符串或多个部分。
* 采样： `temperature` (0–2), `top_p` (0–1), `top_k` (>=1), `seed` (int, optional).
* 长度/惩罚： `max_output_tokens` (int), `presence_penalty` and `frequency_penalty` (-2 to 2), `stop` (string|string\[]).
* 工具： `tools` (定义), `tool_choice` (`auto`/`none`/特定工具), `max_tool_calls` (int), `parallel_tool_calls` (bool).
* Logprobs： `logprobs` (bool), `top_logprobs` (0–20).
* 输出： `response_format` (json/text), `metadata` (object passthrough), `stream` (bool), `service_tier`.
* Gateway 附加参数：`usage` (bool，用于请求用量数据)、`meta` (bool，用于包含 meta 块)。

### 返回值

`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` 时则返回 SSE 帧：

```
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.