Pricing
Simple, transparent pricing
Start free with the npm SDK. Upgrade when you need the REST API, compliance reports, team members, or higher limits.
Hobby
For personal projects and exploring Verdicter.
- 10,000 evaluations / month
- npm + Python SDK
- 3 registered agents
- 5 active policies
- 7-day audit log retention
- Runtime enforcement
- Shield prompt scanning
- Sandbox (5 scenarios)
- GitHub Actions integration
- MCP adapter (@verdicter/mcp)
- Identity: credential tracking (20 credentials)
- Escalation approvals (dashboard)
- Community support
- Direct REST API access
- Observe sessions
- Session replay
- Time-based scheduling
- Comply reports
- Cumulative budgets
- Team members
- Webhooks
- SLA
Starter
For solo developers shipping agents to production.
- 50,000 evaluations / month
- npm + Python SDK + direct REST API
- 10 registered agents
- 20 active policies
- 30-day audit log retention
- Runtime enforcement
- Observe: session tracing + replay
- Time-based policy scheduling
- Cumulative budgets
- Shield: custom injection rules
- Sandbox (50 scenarios)
- GitHub Actions integration
- MCP adapter (@verdicter/mcp)
- Identity: credential tracking (100 credentials)
- Escalation approvals (dashboard)
- Email support
- Comply reports
- Team members
- Webhook notifications
- SLA
Pro
For teams running AI agents in production.
- 250,000 evaluations / month
- npm + Python SDK + direct REST API
- Unlimited agents
- Unlimited policies
- 90-day audit log retention
- Runtime enforcement
- Observe: session tracing
- Cumulative budgets
- Shield: custom injection rules
- Comply: SOC 2, GDPR, HIPAA reports
- Sandbox: unlimited scenarios
- GitHub Actions integration
- MCP adapter (@verdicter/mcp)
- Identity: credential tracking (unlimited)
- Team members (shared workspace plan)
- Escalation approvals (dashboard)
- Escalation routing (Slack, Teams, custom webhooks)
- Email support
- Dedicated support
- Custom contracts
30-day money-back guarantee
Enterprise
Coming soonCustom
For organizations with strict compliance requirements at scale.
Free on all plans
Install the SDK in 30 seconds
Works with TypeScript, LangChain, and Vercel AI SDK. No REST API knowledge required.
npm install @verdicter/sdk
| Capability | Hobby | Starter | Pro | Enterprise |
|---|---|---|---|---|
npm + Python SDK @verdicter/sdk on npm, verdicter on pip | ||||
REST API Direct /v1/evaluate endpoint | - | |||
Enforce Runtime policy evaluation | ||||
Observe Session-level tracing + replay | - | |||
Shield Prompt injection detection | ||||
Shield: custom rules User-defined injection patterns | - | |||
Comply SOC 2, GDPR, HIPAA report generation | - | - | ||
Sandbox Multi-step policy testing | ||||
GitHub Actions Policy checks on every PR | ||||
MCP adapter Enforce policies in any MCP server | ||||
Identity Agent credential tracking (20 / 100 / unlimited) | ||||
Time-based scheduling Policies active only in time windows | - | |||
Budgets Cumulative spend and rate caps | - | |||
Escalation approvals Human review for high-risk actions | ||||
Webhooks Slack, Teams, and custom webhook routing | - | - | ||
Team members Shared workspace | - | - | ||
SSO / SAML Enterprise identity provider | - | - | - |
Frequently asked questions
What's the difference between the SDK and the REST API?
The npm and Python SDKs wrap the REST API with retries, error handling, and framework adapters for LangChain and Vercel AI SDK. Direct REST API access is available on Starter and above - useful for Go, Ruby, or any language without an official SDK.
What counts as an evaluation?
Every call to verdicter.evaluate() - or a direct POST to /v1/evaluate - counts as one evaluation, regardless of the decision (ALLOW, DENY, or ESCALATE).
Does Shield scanning count as an evaluation?
No. Shield scans are tracked separately and are not deducted from your evaluation quota.
Can I upgrade or downgrade at any time?
Yes. Changes take effect at the start of your next billing cycle.
What happens when I exceed my monthly evaluation limit?
Additional evaluations are blocked until your quota resets on the 1st of the next month. You can upgrade at any time to restore access immediately.
Is my agent payload data stored securely?
Yes. All evaluation data is logically isolated per account - every record is scoped to your API key and no other customer can access it. API keys are stored as hashes and never in plaintext. Every evaluation is written as an immutable audit log entry that you can inspect and export from the dashboard.
Do you offer a free trial of Pro?
The Hobby plan is free forever and includes full SDK access with 10,000 evaluations/month. Reach out if you'd like a Pro trial for your team.