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

# Traces

> Live requests and telemetry from a deployment

A deployment records every request it serves as a trace: the request, the response, and the telemetry around it. Traces show what the model does in production, and they are the raw material for [continuous retraining](https://docs.trymonte.ai/continual-learning/continuous-retraining.md).

## Trace Contents

| Field | Description |
| - | - |
| `trace_id` | The ID of the trace, also returned in the `Monte-Request-Id` response header |
| `deployment`, `version` | The deployment and the version that served the request, with its checkpoint |
| `timestamp` | When the request arrived |
| `request` | The messages, tools, and sampling settings the app sent |
| `response` | The model's reply, with each tool call |
| `finish_reason` | Why the reply ended, such as `stop`, `tool_calls`, or `length` |
| `usage` | Tokens in and tokens out |
| `latency` | Time in the queue, time to first token, and total time |
| `status` | The HTTP status, and the error code for a failed request |
| `metadata` | Tags the app sends in the request's `metadata` field, such as a session or customer ID |

## Live Metrics

The same telemetry, rolled up per version: requests, error rate, time to first token, latency at p50 and p95, and output tokens per second.

```bash theme={null}
monte deployment show support-triage --metrics
```

The Console shows the metrics over time under **Inference**, next to the traces.

## View Traces in the Console

1. Click **Inference** in the sidebar.
2. Select the deployment, then the **Traces** tab.
3. Filter by version, status, time range, latency, or a `metadata` tag, and click a row to open the trace.

## Export Traces

```bash theme={null}
monte trace download --deployment support-triage --since 7d -o week.jsonl
```

Each line is one trace as a chat `messages` row, the format of an [SFT dataset](https://docs.trymonte.ai/datasets/overview.md), with the fields above alongside. [Continuous Retraining](https://docs.trymonte.ai/continual-learning/continuous-retraining.md) shows how reviewed traces become training data.

## Collection

Collection is on by default. `--traces off` on a deployment keeps no request or response content; the live metrics stay. With BYOC, traces stay in artifact storage in the team's account. The Console shows them only when **Team** → **Data Sharing** allows it, and `monte trace download` reads them with the member's cloud credentials.


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