Skip to main content
Tokonomics gives you control over how much you spend on AI every month. You set a budget, choose where you want to be notified, and Tokonomics handles the rest — firing alerts as you approach your limit and, on Pro, refusing requests the moment you exceed it. Budget controls apply to your entire account’s LLM spend routed through the proxy.

​
Budget thresholds

Set your monthly budget in the Tokonomics dashboard under Settings → Budget. Once a budget is configured, Tokonomics tracks cumulative spend across all proxied requests for the current calendar month and fires an alert each time you cross a configurable threshold. The default thresholds are 50%, 80%, and 100% of your monthly budget. You can adjust these percentages to match your team’s escalation policy — for example, adding a 90% threshold if you want an extra warning before hitting the cap.
Budget thresholds reset at the start of each calendar month. Mid-month budget changes take effect immediately against the spend already accumulated in the current month.

​
Alert channels

When a threshold is crossed, Tokonomics can notify you through any of the following channels. Configure them in Settings → Alerts.

Slack

Post a message to any Slack channel using an incoming webhook URL.

Microsoft Teams

Deliver an alert card to a Teams channel via a Teams webhook connector.

Email

Send an email to one or more addresses on your account.

Webhook

POST a JSON payload to any URL — compatible with n8n, Zapier, Make, Flowise, and LangFlow for automated workflows.
The webhook payload includes the threshold crossed, current spend, budget amount, and a timestamp, giving downstream automations enough context to act without a follow-up API call.

​
Hard spending caps (Pro)

Pro plan accounts can go beyond alerts and enforce a hard cap that blocks further LLM requests once your monthly budget is exhausted. When the hard cap is enabled and your spend reaches 100% of the configured budget, Tokonomics returns the following error for every subsequent proxied request until the month rolls over: 
HTTP/1.1 429 Too Many Requests
Retry-After: <seconds until month reset>
Content-Type: application/json

{
  "error": "Budget cap reached",
  "message": "Monthly spending cap exceeded"
}
Your application should handle 429 responses from the Tokonomics proxy and surface a meaningful message to users rather than retrying immediately. The Retry-After header tells you exactly how many seconds remain until the monthly budget resets.
Enabling a hard cap means your application will stop receiving LLM responses once the cap is hit — even for latency-sensitive or user-facing features. Test your error-handling logic in a staging environment before enabling hard caps in production.

​
Free vs Pro

Free plan — Budget alerts via all supported channels. Hard spending caps are not available; requests continue after the budget threshold is crossed.Pro plan — Budget alerts plus optional hard spending caps that enforce a strict monthly ceiling.See the full comparison on the Plans page.
To walk through setting up your first budget alert end-to-end, see the Budget Alerts guide.