Request Logs
Overview
The Request Logs page provides a comprehensive view of all API requests made to the Wuliang AI platform. You can filter, search, and analyze individual requests to debug issues, monitor performance, and understand usage patterns. Each log entry contains detailed information about the request, response, and internal processing trace.
Prerequisites
- A registered Wuliang AI account
- At least one API request has been made. See Make API Calls for instructions.
- Logged in to the console
Access Request Logs
In the console sidebar, navigate to Resources > Request Logs.
The request logs page loads with your most recent API requests.
Filter and Search
Use the filter bar at the top of the page to narrow down the log entries.
Available Filters
| Filter | Description |
|---|---|
| Application | Filter by application name |
| API Key | Filter by a specific API Key |
| Capability Type | Filter by capability (Text Generation, Image Generation, etc.) |
| Request ID | Search by exact request ID |
| Date Range | Filter by time period (today, last 7 days, last 30 days, custom range) |
| Source | Filter by request source (OpenAPI, Playground, SDK) |
Apply Filters
Click a filter dropdown to view available options.
Select the desired filter value.
Multiple filters can be applied simultaneously. Active filters are displayed as tags.
Click the Reset button to clear all filters.
Request List
The request list table displays your API requests with the following columns:
| Column | Description |
|---|---|
| Request ID | Unique identifier for the request (click to view details) |
| Time | When the request was made |
| Capability Type | The type of API capability used |
| Status | Success or failure indicator with color coding |
| Tokens (Input) | Number of input tokens consumed |
| Tokens (Output) | Number of output tokens generated |
| Latency | Total response time in milliseconds |
| Client IP | IP address of the requesting client |
Sort and Paginate
Click column headers to sort the list by that field.
Use the pagination controls at the bottom to navigate through pages.
Request Detail Drawer
Click any row in the request list to open a detail drawer with complete request information.
Request Information
The detail drawer displays the following sections:
| Section | Description |
|---|---|
| Request ID | Unique identifier |
| Timestamp | Exact date and time of the request |
| Application | The application associated with the request |
| API Key | The key used (masked for security) |
| Model | The AI model called |
| Capability Type | The API capability used |
| Source | Where the request originated (OpenAPI, Playground, SDK) |
| Status | Success or failure with HTTP status code |
| Client IP | IP address of the requester |
Request Parameters
The full request body as sent to the API, including model, messages, temperature, and all other parameters.
Response Data
The complete API response including generated content, token usage, and finish reason.
Error Details
For failed requests, the error code, message, and troubleshooting information are displayed.
Token Usage Breakdown
A detailed breakdown of token consumption:
| Metric | Description |
|---|---|
| Input Tokens | Tokens in the request prompt |
| Output Tokens | Tokens in the generated response |
| Total Tokens | Combined input and output tokens |
| Cost | Monetary cost of the request |
Request Trace Timeline
For each request, a trace timeline visualizes the internal processing stages. This is particularly useful for diagnosing performance issues or understanding where failures occur.
Trace Spans
Each span in the timeline represents a processing stage:
| Span Field | Description |
|---|---|
| Name | The processing stage name (e.g., Authentication, Model Routing, Inference, Response) |
| Duration | Time spent in this stage |
| Status | Success or failure |
| Error Info | Error details if the span failed |
Using the Trace for Debugging
Identify slow requests by sorting the list by latency (descending).
Open the request detail and examine the trace timeline.
Identify which processing stage consumed the most time or where the error occurred.
Use the request ID to correlate with your application logs for end-to-end debugging.
Common Use Cases
Debug a Failed Request
Filter the list by Status to show only failed requests.
Click the failed request to open the detail drawer.
Review the error details and trace timeline to identify the root cause.
Investigate High Latency
Sort the list by Latency in descending order.
Open the top entries and examine the trace timeline to find the slowest processing stage.
Track Usage by Application
Filter by a specific Application to see all requests for that app.
Review the token consumption and cost breakdown.
Notes
- Request logs are retained for 30 days by default. Contact support for extended retention.
- The detail drawer masks sensitive information such as full API Keys.
- Log data may have a slight delay (up to 5 minutes) before appearing in the list.
- The request ID can be used to search for specific requests across different filter combinations.
- Trace timeline data is available for all requests, regardless of success or failure.
Related Documentation
- Make API Calls - Learn how to make API requests
- Manage API Keys - Create and configure API Keys
- Application Detail - View request logs scoped to a specific application
- Models & Pricing - Browse available models and understand pricing