> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orq.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# AI Gateway traces
> Inspect every AI Gateway request as a detailed trace. View latency, token usage, cache hits, and provider responses for each routed call.
## What are Traces
**Traces** provide visibility into the workflow of each model generation and revealing the inner workings of an LLM call on **the AI Gateway**.
Traces correspond to events within the generations, following each call to the model configured in the **AI Gateway**.
### Use Cases
* **Monitor Performance**: Identify bottlenecks by checking which operations take the most time. Optimize prompts or model selections accordingly.
* **Track Costs**: See exactly which operations are consuming tokens and costing money. Understand the cost breakdown across different models and operations.
* **Debug Issues**: When something goes wrong, traces show exactly where in the request pipeline the failure occurred, helping identify root causes.
* **Optimize Routing**: For AI applications using model routing, traces show which models were selected and how the routing logic performed.
* **Analyze Request Flow**: Understand how requests are processed by seeing the complete operation hierarchy and dependencies.
## Viewing Traces
To view Traces, go to **Traces** in the **AI Gateway** sidebar.
The following details are available to visualize:
* **Request Timeline**: A hierarchical breakdown of all operations that occurred during the request, from routing decisions to model invocations.
* **Operation Details**: Each step in the trace shows:
* Model used and provider information.
* Token consumption (input/output).
* Cost for that specific operation.
* Status and any error information.
* **Request Metadata**:
* Unique trace ID for tracking.
* Total request duration.
* Aggregated token usage and cost.
## Filtering Traces
You can filter traces to find specific requests or focus on particular aspects of AI Gateway calls:
| Filter | Description |
| --------------------- | --------------------------------------------------------------- |
| **Model** | Filter by specific models used (e.g., gpt-5, claude-sonnet-4-6) |
| **Provider** | Filter by provider (e.g., OpenAI, Anthropic, Google) |
| **Status** | Filter by request status (Success, Error, etc.) |
| **Cost Range** | Filter traces by cost (minimum and maximum values) |
| **Duration** | Filter by request execution duration |
| **Date Range** | Filter traces by when they were created |
| **Custom Attributes** | Filter by metadata or custom attributes attached to requests |
To apply filters, use the **button**. Combine multiple filters to narrow down your results.
## Managing Columns
Show and hide columns to display the most relevant data.
**To customize columns:**
* Look for the **button** in the traces table header
* Toggle columns on or off to show/hide specific data such as:
* Model, Provider, Status
* Token usage (input/output)
* Cost, Duration, Latency
* Trace ID, Timestamp
* Custom metadata fields
## Creating Custom Views
Save frequently used filter combinations as reusable views that can be shared across the team.
**To create a custom view:**
1. **Set the desired filters** - Apply the desired filters (e.g., filter by model, status, date range)
2. Click All Rows (top right)
3. Select Create New View
4. **Give the view a title** - Enter a descriptive name (e.g., "GPT-4o Errors", "High-Cost Requests")
5. Choose **Make this view private** to keep this view personal (not shared with team members).
6. **Save** - Your filtered view is now created and accessible
Click All Rows at the top right to see all available views. Select any saved view to instantly apply those filters and see the relevant traces.
## Reference
Complete reference for all `orq.*` span attributes in **AI Gateway** traces, webhook payloads, and trace exports.