> ## 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.

# 查询生成记录

> 调用 /generations 检索之前的生成记录。

**方法**：`client.GetGeneration(...)`

### 示例

```csharp theme={null}
using PhaseoSdk;

var client = new Phaseo(apiKey);
var response = await client.GetGeneration("G-01ABC...");
```

### 参数

* `id`（string，必填）：之前调用返回的请求 ID。

### 返回值

生成记录（JSON）

如果网关保存了完整请求详情，返回记录会包含 `replay_supported` 和 `replay_request`。你可以将 `replay_request` 发回原端点，以受控方式重新运行请求。

时间字段遵循网关统一的语义：

* `latency_ms`：记录到的首个 token 或首个输出字节/帧的耗时
* `generation_ms`：记录到的首个响应延迟之后的生成耗时

```json theme={null}
{
	"created_at": "2026-05-05T12:00:00.000Z",
	"request_id": "G-01ABC123",
	"team_id": "team-123",
	"app_id": "app-123",
	"endpoint": "chat/completions",
	"model_id": "openai/gpt-4o-mini",
	"provider": "openai",
	"native_response_id": "chatcmpl-123",
	"stream": false,
	"byok": false,
	"status_code": 200,
	"success": true,
	"error_code": null,
	"error_message": null,
	"latency_ms": 1500,
	"generation_ms": 1400,
	"usage": {
		"prompt_tokens": 9,
		"completion_tokens": 9,
		"total_tokens": 18
	},
	"cost_nanos": 1000000,
	"currency": "USD",
	"pricing_lines": [],
	"key_id": "key-123",
	"throughput": null,
	"replay_supported": true,
	"replay_request": {
		"model": "openai/gpt-4o-mini",
		"messages": [
			{ "role": "user", "content": "Say hello" }
		]
	}
}
```


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