Skip to main content
Tokonomics tracks your cumulative AI spend in real time and fires alerts the moment you cross a threshold you define. You set a monthly budget, choose which percentages trigger a notification, and configure where those notifications go — Slack, Teams, email, or any HTTPS webhook endpoint. No polling, no manual checks, no surprise invoices.
1

Set a monthly budget

Navigate to Dashboard → Settings → Budget and enter your monthly cap in USD. Tokonomics uses this figure as the baseline for all threshold calculations. You can update it at any time; changes take effect immediately.
2

Choose alert thresholds

Select which spend percentages should trigger an alert. The available thresholds are 50%, 80%, and 100%. You can enable any combination — for example, enable 80% and 100% if you only want a warning near the limit and a final alert when you hit it. Each threshold can route to its own channel.
3

Configure alert channels

Choose where each alert is delivered.
Paste your Slack incoming webhook URL into the Slack webhook URL field. Tokonomics sends a formatted message that includes the threshold, current spend, and budget total.
https://hooks.slack.com/services/T00000000/B00000000/XXXXXXXXXXXXXXXXXXXXXXXX
4

Test the alert

Click Send test next to any configured channel in the dashboard. Tokonomics immediately delivers a sample payload so you can confirm the integration is working before you hit a real threshold.

​
Webhook payload

When a threshold is crossed, Tokonomics POSTs the following JSON body to your webhook URL: 
{
  "event": "budget.threshold",
  "threshold_percent": 80,
  "current_spend": 40.00,
  "monthly_budget": 50.00,
  "budget_used_percent": 80.0
}
FieldTypeDescription
eventstringAlways budget.threshold
threshold_percentnumberThe threshold that was crossed (50, 80, or 100)
current_spendnumberYour cumulative spend in USD at the time of the alert
monthly_budgetnumberYour configured monthly cap in USD
budget_used_percentnumberExact percentage used, which may exceed the threshold slightly

​
Hard caps (Pro)

Pro plan users can enable a hard cap in addition to alerts. When your spend reaches 100% of your monthly budget and the hard cap is active, Tokonomics rejects further requests with a 429 Too Many Requests response until the budget resets or you increase your cap. This prevents runaway spend caused by loops or unexpected traffic spikes.
Hard caps block all proxied requests once the budget is exhausted — including production traffic. Test your alerting and response handling at the 80% threshold before enabling this feature.
Alert delivery is best-effort. Tokonomics retries failed deliveries up to 3 times with exponential backoff before marking the alert as undelivered. You can see the delivery status of every alert in Dashboard → Settings → Alert History.
For more detail on how budgets are calculated and reset, see Budgets.