Airlock has two layers of control over usage: your plan, which determines how many integrations you can deploy, and per-integration token budgets that cap how many LLM tokens each integration can spend.
Plans
Airlock has no self-service billing portal. Whether your organization has an active subscription is a flag that Airlock sets for you — paid plans are arranged directly with Airlock (for example, by invoice or contract) rather than through an in-app checkout.
Free tier (no active subscription): you can deploy up to 5 integrations. Existing integrations keep working as normal; when you try to add a sixth, Airlock blocks it with a "Free plan limit reached" message asking you to contact us to enable more.
With an active subscription: the cap is lifted — you can deploy an unlimited number of integrations.
To raise your limit, contact Airlock.
Per-Integration Token Budgets
Every integration can have an independent token budget that caps how many LLM tokens its tool calls may consume. Budgets are configured on the integration detail page under Budget.
Available controls:
- Hard limit — when crossed, further tool calls on that integration return an error until the budget resets or is raised. Use this to prevent runaway spend.
- Soft limit — a warning threshold that triggers an alert email but does not block calls.
- Alert thresholds — percentages of the configured limit (the hard limit if set, otherwise the soft limit) at which Airlock sends notifications (e.g.,
[50, 75, 90]sends three escalating warnings). - Notify emails — list of addresses to email when thresholds cross.
A background job evaluates budgets hourly and sends alerts. Hard-limit enforcement is real-time on each tool call.
Typical setup:
Soft limit: 2,000,000 tokens (warning)
Hard limit: 3,000,000 tokens (block)
Alert thresholds: [50, 75, 90] (% of hard limit)
Notify emails: ops@example.comRequest Counting
Airlock counts MCP requests per period across all your integrations, but this is for usage visibility only — there is no request cap, and tool calls are never rejected for hitting a request count. The running totals feed the Usage and Analytics pages; spend is controlled by the per-integration token budgets above.
Usage Visibility
| Page | What it shows |
|---|---|
| /usage | Per-user breakdown of token usage in the current period |
| /analytics | Org-wide call volume, success rates, and tool usage |
| Integration detail page | That integration's usage and remaining budget |
All MCP tool calls are also written to the audit log, accessible from the History page in the main navigation.