Plans
PromptGuard offers three self-service plans and an Enterprise option for organizations that need full control.Free
$0/monthPerfect for evaluation and small projects.
- 10,000 requests/month
- 1 project, 1 API key
- Regex-based threat detection
- Basic PII redaction
- Auto-instrumentation for all LLM SDKs
- 24-hour log retention
- Community support
Pro
$49/monthFor production applications needing reliable security.
- 100,000 requests/month
- 5 projects, 5 API keys
- ML + LLM-enhanced detection (F1 = 0.887, 99.1% precision)
- All 10 detector types
- Custom security policies
- 7-day log retention
- Email alerts & support
Scale
$149/monthFor high-volume applications.
- 1,000,000 requests/month (soft limit)
- Unlimited projects & API keys
- ML + LLM-enhanced detection
- Advanced analytics
- 30-day log retention
- Priority support (24hr)
- 99.9% uptime SLA
Enterprise
For organizations that need team management, SSO, compliance controls, and custom infrastructure.Organizations & RBAC
Team workspaces with role-based access control. Owner, Admin, Member, and Viewer roles with granular permissions.
SSO (OIDC)
Single sign-on via Okta, Azure AD, Google Workspace, or any OIDC-compliant provider. Per-org IdP configuration with auto-provisioning.
Audit Logs & GDPR
Persistent SOC 2-ready audit trail with integrity hash chaining. GDPR data export and deletion endpoints.
Security Controls
IP allowlisting, webhook signing (HMAC-SHA256), project-scoped API key management, and custom log retention.
Custom Limits
Custom monthly request quotas, rate limits, and retention periods configured per organization.
Dedicated Support
Custom SLAs, 4-hour response time, dedicated account manager, and onboarding support.
Contact sales@promptguard.co for Enterprise pricing, or book a call.
Feature Comparison
| Feature | Free | Pro | Scale | Enterprise |
|---|---|---|---|---|
| Monthly requests | 10,000 | 100,000 | 1,000,000 | Custom |
| Projects | 1 | 5 | Unlimited | Unlimited |
| API keys | 1 | 5 | Unlimited | Unlimited |
| Over-limit behavior | Hard block | Hard block | Soft limit | Soft limit |
| Regex-based detection | Yes | Yes | Yes | Yes |
| ML-enhanced detection | — | Yes | Yes | Yes |
| LLM-based detection | — | Yes | Yes | Yes |
| Secret key detection | — | Yes | Yes | Yes |
| URL filtering | — | Yes | Yes | Yes |
| Jailbreak LLM detection | — | Yes | Yes | Yes |
| Tool injection detection | — | Yes | Yes | Yes |
| Custom policies | — | Yes | Yes | Yes |
| PII redaction | Yes | Yes | Yes | Yes |
| Auto-instrumentation | Yes | Yes | Yes | Yes |
| Guard API | Yes | Yes | Yes | Yes |
| Agent Security API | Yes | Yes | Yes | Yes |
| Framework integrations | Yes | Yes | Yes | Yes |
| Log retention | 24 hours | 7 days | 30 days | Custom |
| Advanced analytics | — | — | Yes | Yes |
| Email alerts | — | Yes | Yes | Yes |
| Audit logs | — | — | — | Yes |
| GDPR export/deletion | — | — | — | Yes |
| Organizations & RBAC | — | — | — | Yes |
| SSO (OIDC) | — | — | — | Yes |
| IP allowlist | — | — | — | Yes |
| Webhook signing | — | — | — | Yes |
| Custom retention | — | — | — | Yes |
| Idempotency keys | Yes | Yes | Yes | Yes |
| Rate limit headers | Yes | Yes | Yes | Yes |
| Support | Community | Priority | Dedicated | |
| Uptime SLA | — | — | 99.9% | 99.95% |
Integration Methods
All plans include every integration method:| Method | Description | Best For |
|---|---|---|
| Auto-instrumentation | promptguard.init() — one line secures all LLM calls | Most applications |
| Guard API | POST /api/v1/guard — scan content directly | Custom workflows |
| HTTP Proxy | Change base URL to api.promptguard.co | Drop-in replacement |
| Framework integrations | Native callbacks for LangChain, Vercel AI SDK | Framework users |
Rate Limits
Monthly Request Quotas
| Plan | Limit | Behavior When Exceeded |
|---|---|---|
| Free | 10,000 | Returns 429 Too Many Requests |
| Pro | 100,000 | Returns 429 Too Many Requests |
| Scale | 1,000,000 | Continues processing + email alerts |
| Enterprise | Custom | Continues processing + alerts |
Infrastructure Rate Limiting
All plans share the same anti-abuse rate limit:- 100 requests per minute per IP address (enforced by Cloud Armor)
- This is a security measure, not a pricing feature
- Contact sales@promptguard.co for higher limits
How Usage Is Calculated
One request = one API call to any of these endpoints:| Endpoint | Counts as |
|---|---|
POST /api/v1/chat/completions | 1 request |
POST /api/v1/completions | 1 request |
POST /api/v1/guard | 1 request |
POST /api/v1/agent/validate-tool | 1 request |
PromptGuard uses a pass-through model: you provide your own LLM API keys (OpenAI, Anthropic, etc.), and PromptGuard only charges for security services. LLM costs go directly to your provider.
FAQ
Can I change plans at any time?
Can I change plans at any time?
Yes. Upgrade or downgrade at any time. Upgrades take effect immediately; downgrades at the next billing cycle.
What happens if I exceed my request limit?
What happens if I exceed my request limit?
Free and Pro plans return
429 Too Many Requests. Scale and Enterprise plans use soft limits — your app keeps running and you receive alerts.Do you offer a free trial?
Do you offer a free trial?
The Free tier (10,000 requests/month) lets you fully evaluate PromptGuard. Paid plans have a 14-day money-back guarantee.
Can I self-host PromptGuard?
Can I self-host PromptGuard?
Yes. Enterprise customers can deploy PromptGuard on their own infrastructure — cloud, on-premise, or fully air-gapped with no external API calls. Contact sales for details.
What payment methods do you accept?
What payment methods do you accept?
All major credit cards via Stripe. Enterprise customers can arrange invoice billing.
Do failed or blocked requests count against my quota?
Do failed or blocked requests count against my quota?
Yes. Every API call counts, including retries and blocked requests.