Skip to main content
NexLLM gives you two complementary tools for understanding how your account uses the API: granular Usage Logs that record every individual request, and an interactive Dashboard that visualises trends and consumption patterns over time. Together they help you stay on top of costs, debug unexpected usage, and optimise your model choices.

Usage Logs

The Usage Logs page provides a full, per-request history of every API call your account has made. Open it by clicking Logs in the left sidebar. Each row in the log table represents one API call and displays the following fields:
ColumnDescription
Request TimeThe date and time the request was received.
API Key NameThe name of the API key used to authenticate the request.
Model NameThe model that handled the request.
TimingHow long the request took to complete.
Token ConsumptionThe number of input and output tokens used.
CostThe quota deducted for this request.

Search and Filter Logs

Use the filter bar above the log table to narrow down your records to exactly what you need.
1

Set a time range

Under Time Range, select a start date and an end date to limit results to requests made within that window.
2

Filter by model (optional)

In the Model field, type a model name or keyword. The results will include only requests that match your entry.
3

Filter by group (optional)

In the Group field, enter the name of the channel group you want to inspect.
4

Apply the filters

Click Search. The log table refreshes and displays only the records that match your selected criteria.

Usage Statistics (Dashboard)

The Dashboard gives you a bird’s-eye view of your API activity through charts and summary metrics. Navigate to it by clicking Dashboard in the left sidebar.

Key Metrics

At the top of the Dashboard you will find five summary statistics for the selected time period:

Total Requests

The total number of API calls made in the selected period.

Quota Consumption

The total quota deducted across all requests.

Token Usage

The combined input and output tokens consumed.

Average RPM

The average number of requests per minute over the period.

Average TPM

The average number of tokens per minute over the period.

Time Range and Preferences

Use the Filter controls to choose what data the Dashboard displays:
  • Quick ranges — Select 1 Day, 7 Days, 14 Days, or 29 Days for instant presets.
  • Custom range — Pick any start and end date. The maximum custom duration is 1 month.
The Preferences panel lets you save your preferred defaults — including the default time range, time granularity, consumption chart type, and model call chart type — so the Dashboard always opens with the view you find most useful.
Use the Quota Distribution chart to pinpoint high-cost time periods within a day or week. Once you spot a spike, cross-reference it with the Usage Logs filtered to that same window to identify which API key and model drove the increase.

Quota Distribution

The Quota Distribution section shows how your quota spend breaks down across the selected time range, giving you a clear picture of when and where resources are being consumed. From this chart you can:
  • Review daily or hourly quota consumption trends.
  • Compare quota usage across different models to see which ones cost the most.
  • Identify periods with unusually high consumption that may warrant investigation.
  • Switch between Bar Chart and Area Chart views depending on how you prefer to visualise the data.
  • Hover over any data point to see the exact quota value for that time slice and model.

Model Call Analytics

The Model Call Analytics section focuses on request volume rather than cost, showing you how frequently each model is called during the selected period. You can use this section to:
  • Monitor your total model call volume over time.
  • View call trends to see whether activity is rising or falling.
  • Compare request activity between models to understand which ones you rely on most.
  • Identify the most frequently called models across your account.
  • Switch between three dedicated views:
    ViewWhat it shows
    Call TrendA time-series chart of call volume over the selected period.
    Call Count DistributionA breakdown of total calls by model.
    Call Count RankingModels ranked by total call count, highest first.
  • Hover over the chart to view exact call counts for any point in time.