Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.promptguard.co/llms.txt

Use this file to discover all available pages before exploring further.

Plans

PromptGuard has three self-service tiers and an Enterprise tier. All tiers include the full detection pipeline (regex, ML, and LLM-based detection).

Free

$0/month
  • 10,000 requests/month
  • 1 project, 1 API key
  • All detectors (ML + LLM)
  • PII detection and redaction
  • 24-hour log retention
  • Community support

Pro

$99/month
  • 100,000 requests/month
  • 5 projects, 5 API keys
  • Custom security policies
  • 7-day log retention
  • Email alerts and support

Scale

$199/month
  • 1,000,000 requests/month (soft limit)
  • Unlimited projects and API keys
  • Advanced analytics
  • 30-day log retention
  • Priority support (24hr)
  • 99.9% uptime SLA

Enterprise

Enterprise adds team management, SSO, compliance controls, and custom infrastructure options.

Organizations and RBAC

Team workspaces with role-based access control (Owner, Admin, Member, Viewer).

SSO (OIDC)

Single sign-on via Okta, Azure AD, Google Workspace, or any OIDC-compliant provider.

Audit Logs and Compliance

Persistent audit trail with integrity hash chaining. GDPR data export and deletion endpoints.

Security Controls

IP allowlisting, webhook signing (HMAC-SHA256), and custom log retention.

Custom Limits

Custom monthly request quotas, rate limits, and retention periods per organization.

Dedicated Support

Custom SLAs and dedicated account manager.
Contact sales@promptguard.co for Enterprise pricing.

Feature Comparison

FeatureFreeProScaleEnterprise
Monthly requests10,000100,0001,000,000Custom
Projects15UnlimitedUnlimited
API keys15UnlimitedUnlimited
Over-limit behaviorHard blockHard blockSoft limitSoft limit
Regex-based detectionYesYesYesYes
ML-enhanced detectionYesYesYesYes
LLM-based detectionYesYesYesYes
Secret key detectionYesYesYesYes
URL filteringYesYesYesYes
Jailbreak LLM detectionYesYesYesYes
Tool injection detectionYesYesYesYes
Content safety classificationYesYesYesYes
Multi-turn drift detectionYesYesYesYes
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:
  • 600 requests per minute per IP address
  • Health-check and CORS preflight paths are exempt
  • Enterprise customers can request 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) includes the full detection pipeline. Use it to evaluate before upgrading.
Self-hosted deployment is available for Enterprise customers. Contact sales@promptguard.co for details.
Yes. Every API call counts, including retries and blocked requests.