Dashboard Overview – Monitor Your LLM API Usage

The Dashboard is the landing page of the AIsa Console. It summarizes spend, traffic, and account health for the last 30 days, so you can tell at a glance whether your integration is working and how your usage is trending. The usage figures — spend, requests, and model split — cover a fixed 30-day window. Balance, key, and account details are current state, not a windowed total. For arbitrary date ranges, per-request detail, or filtering by key and model, use Usage & Logs.

​

Header Actions

Two shortcuts sit next to the page title:

• New API Key opens API Keys to create a key
• Top Up opens Billing to add balance

If a first top-up promotion is active on your account, the Top Up button shows the discount and a banner appears above the metrics with the remaining time.

​

Metric Cards

The top row is the fastest read on account state. Total Balance is the credit available for API spend. It is drawn down automatically as requests are processed. Spend · 30D is what your traffic cost over the last 30 days, with the daily average below it. Requests · 30D is the number of API calls in the same window. The subtitle shows the error rate — the share of those calls that failed. A rate climbing above your normal baseline is usually the first sign of a bad key, an unavailable model, or a malformed request. Active Keys shows enabled keys out of total keys, plus when any key was last used. If it reads No key activity yet, no request has ever been made with your keys.

​

Spend and Requests Charts

Two charts break the same 30-day totals down by day. Spend is plotted in USD per day, Requests in calls per day. The value above each chart repeats the 30-day total, and the number in the top-right corner marks the peak day. Hover — or focus the chart and use the left and right arrow keys — to read the exact value and date for any single day. The labels below the line mark the start, middle, and end of the window. Reading the two charts together separates a traffic spike from a cost spike: requests flat but spend rising usually means a shift toward more expensive models or longer contexts.

​

Model Split

Model Split shows which models your traffic actually went to. Each row lists a model, its call count for the last 30 days, and its share of total calls. View usage opens Usage & Logs for the full breakdown. If nothing has been called in the window, the panel reports that no model data is available.

​

Account

The Account panel shows your current identity and access status:

• Display name and email
• Account type — your current plan tier
• Security — Verified or Pending, reflecting email verification
• Member since — account creation date
• Last sign-in — time of your most recent login

​

When Data Fails to Load

If balance, key, or usage data cannot be fetched, an inline warning appears at the top of the page with a Refresh button that retries all three requests at once.

​

Related