Skip to main content

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

FeatureFreeProScaleEnterprise
Monthly requests10,000100,0001,000,000Custom
Projects15UnlimitedUnlimited
API keys15UnlimitedUnlimited
Over-limit behaviorHard blockHard blockSoft limitSoft limit
Regex-based detectionYesYesYesYes
ML-enhanced detectionYesYesYes
LLM-based detectionYesYesYes
Secret key detectionYesYesYes
URL filteringYesYesYes
Jailbreak LLM detectionYesYesYes
Tool injection detectionYesYesYes
Custom policiesYesYesYes
PII redactionYesYesYesYes
Auto-instrumentationYesYesYesYes
Guard APIYesYesYesYes
Agent Security APIYesYesYesYes
Framework integrationsYesYesYesYes
Log retention24 hours7 days30 daysCustom
Advanced analyticsYesYes
Email alertsYesYesYes
Audit logsYes
GDPR export/deletionYes
Organizations & RBACYes
SSO (OIDC)Yes
IP allowlistYes
Webhook signingYes
Custom retentionYes
Idempotency keysYesYesYesYes
Rate limit headersYesYesYesYes
SupportCommunityEmailPriorityDedicated
Uptime SLA99.9%99.95%

Integration Methods

All plans include every integration method:
MethodDescriptionBest For
Auto-instrumentationpromptguard.init() — one line secures all LLM callsMost applications
Guard APIPOST /api/v1/guard — scan content directlyCustom workflows
HTTP ProxyChange base URL to api.promptguard.coDrop-in replacement
Framework integrationsNative callbacks for LangChain, Vercel AI SDKFramework users

Rate Limits

Monthly Request Quotas

PlanLimitBehavior When Exceeded
Free10,000Returns 429 Too Many Requests
Pro100,000Returns 429 Too Many Requests
Scale1,000,000Continues processing + email alerts
EnterpriseCustomContinues 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:
EndpointCounts as
POST /api/v1/chat/completions1 request
POST /api/v1/completions1 request
POST /api/v1/guard1 request
POST /api/v1/agent/validate-tool1 request
Usage is independent of token count, model used, or response length.
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

Yes. Upgrade or downgrade at any time. Upgrades take effect immediately; downgrades at the next billing cycle.
Free and Pro plans return 429 Too Many Requests. Scale and Enterprise plans use soft limits — your app keeps running and you receive alerts.
The Free tier (10,000 requests/month) lets you fully evaluate PromptGuard. Paid plans have a 14-day money-back guarantee.
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.
All major credit cards via Stripe. Enterprise customers can arrange invoice billing.
Yes. Every API call counts, including retries and blocked requests.