Pricing
Deterministic enforcement costs for production automations. Measured in protected actions.
AI Safety Gate pricing
How billing works
One validation call before an action counts as one protected action.
COUNTS AS 1
validate()
A single request producing PASS/WARN/BLOCK.ⓘ
BEST PRACTICE
Gate every irreversible step
Money, messaging, CRM writes, production updates.
Enterprise consideration
Audit retention scales
Higher tiers keep longer logs for investigations.
What is a protected action?
Natural-language definition for production usage.
A protected action is a workflow step guarded by AI Safety Gate. In practice, it is one call to validate() made immediately before an irreversible step (money, messaging, CRM write, production update). The returned PASS/WARN/BLOCK decision determines whether your automation continues, routes to review, or stops.
Audit retention scales with higher plans so teams can investigate incidents, demonstrate controls, and support operational requirements without changing enforcement behavior.
FREE
50 protected actions / month
$0
/ mo
Rule complexityBasic rules
Managed Safety ModeAlways enforced for safety
Logs & auditing7 days
WARN handlingWARN handling: Auto-block
Charts + analyticsLocked
SupportDocumentation only
Starter
3,000 protected actions / month
$29
/mo
Rule complexityAdvanced rules + approvals
Logs & auditing7 days
WARN handlingWARN approval (approve / reject)
Managed Safety ModeConfigurable (can be disabled)
SupportPriority support
Charts + analyticsIncluded
For evaluation and early testing.
Get startedPro
Recommended
10,000 protected actions / month
$99
/mo
Rule complexityBasic rules
Logs & auditing30 days
WARN handlingWARN handling: Auto-block
Managed Safety ModeAlways enforced for safety
SupportDocumentation support
Charts + analyticsLocked
Fail-closed enforcement
No prompt-only safety
Auditable decisions
Human approval on WARN
Compare plans
Feature access is enforced server-side. If in doubt, the system defaults to the safest posture.
| Feature | Free | Starter | Pro |
|---|---|---|---|
| Managed Safety Mode | Always enforced for safety | Configurable (can be disabled) | Always enforced for safety |
| Rule editing (Policy Control Mode) | Locked | Included | Locked |
| Rule match details | Locked | Locked | Locked |
| WARN approval (approve / reject) | Auto-block | Included | Auto-block |
| Fail-closed on timeout | Included | Included | Included |
| Charts + analytics | Locked | Included | Locked |
| Audit retention duration | 7 days | 7 days | 30 days |
Pricing logic
Infrastructure pricing should be deterministic and auditable.
Protect what matters
You pay for enforcement events—every time AI output is evaluated before an action.
Audit depth by tier
Retention increases as stakes rise so teams can investigate and demonstrate controls.
In v1, retention is enforced at the query/visibility level; data is not physically deleted. See Retention.
Operational support
Higher tiers add tighter response times and onboarding support for critical workflows.