10,000 free requests per month

#1 Firewall for AI Prompts

Protect your LLM applications from prompt injection, data leaks, and AI-specific threats - with real-time visibility and reduced LLM costs.

Start Protecting for FreeBook a Demo
Prompt injection protection
PII detection & redaction
AI agent guardrails
Deploy in minutes
10K
Free requests/mo
99.9%
Uptime SLA
~0.15s
Typical Latency
20+
Threat vectors
Live Gateway Feed

Watch PromptGuard Protect in Real-Time

Every request is scanned, validated, and logged. See the security decisions as they happen.

Total Requests
32,480
Threats Blocked
487
Cache Savings
$542.80
Bots Blocked
68
promptguard-gateway-prod-us-east-1
Live

This is a simulation of real gateway traffic. Actual events may vary.

How It Works

Three steps to production-grade AI security. No complexity, no compromises.

01

Change your base URL

Instant Setup

Update base_url and add X-API-Key header with your PromptGuard API key

02

Configure security rules

Flexible Policies

Use defaults or customize detection rules, PII redaction, and rate limits

03

Monitor everything

Full Visibility

Real-time dashboard shows threats blocked, requests analyzed, and audit logs

No SDK changes required. Works with all popular LLM providers.

Request Flow

Your App
PromptGuard
PromptGuard
LLM Provider
~0.15s typical
app.py
1
import promptguard
2
3
promptguard.init(api_key="pg_...")
4
5
# That's it! All OpenAI, Anthropic, Google,
6
# Cohere, Bedrock calls are now protected.
7
from openai import OpenAI
8
client = OpenAI() # works normally
One line. All LLM calls are now secured.
Live Demo

See PromptGuardIn Action

Click an example below to see how we detect threats, redact PII, and protect your AI apps in real-time

Select an Example:

Selected Prompt

Read-only Demo

Select an example prompt from the left to see PromptGuard in action.

Click an example prompt to see PromptGuard in action

ROI CALCULATOR

See How Much You'll Save

Most companies save 40-60% on LLM costs with PromptGuard. Calculate your potential savings below.

Your Usage

Monthly Requests500K
Avg Tokens/Request1,500
Current Monthly LLM Cost
$22.5K

Your Monthly Savings

$15.8K

70% reduction in LLM costs

Savings Breakdown

Response Caching

45% cache hit rate

$10.1K

Bot Traffic Blocked

25% junk requests eliminated

$5.6K
PromptGuard Cost
-$149/mo
Net Monthly Savings$15.6K
ROI10470%
Complete Security Platform

Everything You Need toSecure AI at Scale

Enterprise-grade security features included by default. AI agent protection, red team testing - no premium tiers required.

Core

Complete AI Security

Protect against prompt injection, jailbreaks, PII leaks, data exfiltration, toxicity, and more. Ten security guardrails with ML and LLM-powered detection.

Popular

AI Agent Security

Validate tool calls before execution. Block dangerous commands, detect privilege escalation, and monitor agent behavior for anomalies in real-time.

New

Red Team Testing

Built-in adversarial testing suite. Run 20+ attack vectors against your policies with one click. Get a security grade and detailed vulnerability report.

New

GitHub Code Scanner

Connect your repos via GitHub App. AST-based scanning detects every unprotected LLM call with zero false positives and raises auto-fix PRs.

Smart Caching & Routing

Response caching reduces redundant LLM calls. Multi-provider routing with automatic failover keeps your app running.

Data Leak Prevention

39+ PII entity types detected and redacted, with optional synthetic data replacement. API keys, secrets, and sensitive data caught in both inputs and outputs.

New

Confidence Scores & Alerts

Every decision includes a confidence score via X-PromptGuard-Confidence header. Webhook and email alerts for threats. Never blindly trust a binary allow/block.

Zero Retention Mode

Enable per-project zero retention to process requests without storing prompt content. Your data stays private.

New

Autonomous Red Team Agent

LLM-powered adversarial search discovers novel attack vectors through intelligent mutation. Get graded security reports with actionable recommendations.

New

Policy-as-Code

Define guardrails in YAML, version in git, apply via CLI. Full config lifecycle management with validation, diffing, and idempotent application.

New

MCP Server Security

Validate Model Context Protocol tool calls before execution. Server allow/block-listing, schema validation, and injection detection.

New

CI/CD Security Gate

GitHub Action runs red team tests on every PR. Configurable minimum grades, regression detection, and automatic PR comments.

Start with 10,000 free requests/month

Explore all features
Industry Solutions

Security forEvery AI Use Case

From autonomous agents to customer support bots, PromptGuard provides specialized protection tailored to your specific needs.

AI Agents & Automation

Secure autonomous agents against indirect prompt injection, validate tool calls before execution, and monitor behavior for anomalies in real-time.

  • Tool call validation
  • Behavior analysis
  • Human-in-the-loop triggers

RAG & Web Scraping

Protect retrieval pipelines from poisoned documents and malicious web content with real-time content scanning.

  • Indirect injection detection
  • Document sanitization
  • URL allowlists

Customer Support Bots

Deploy chatbots that can't be jailbroken, leak customer data, or provide harmful advice. Auto-redact PII from conversations.

  • Jailbreak prevention
  • PII auto-redaction
  • Response filtering

AI Code Assistants

Prevent code injection, block malicious suggestions, and ensure AI coding tools can't access sensitive repos or execute harmful commands.

  • Code injection blocking
  • Repo access control
  • Command validation

Fintech & Banking

PCI-DSS compliant guardrails that prevent unauthorized financial advice, block fraud attempts, and protect transaction data.

  • PCI-DSS compliance
  • Fraud detection
  • Financial PII protection

Healthcare & MedTech

HIPAA-ready protection that redacts PHI, enforces medical disclaimers, and prevents AI from giving dangerous medical advice.

  • HIPAA compliance
  • PHI redaction
  • Medical disclaimer enforcement

Legal & Compliance

Ensure AI tools don't give legal advice, maintain attorney-client privilege, and create audit trails for regulatory requirements.

  • Legal disclaimer enforcement
  • Privilege protection
  • Audit trails

E-commerce & Retail

Automate returns and support while protecting customer PII, preventing refund fraud, and blocking competitor price scraping.

  • Refund fraud prevention
  • Customer data protection
  • Anti-scraping

Don't see your use case? Contact us for a custom security solution.

Verified Performance

Production-Ready Security

Real benchmarks. Measured performance. Built for scale.

~0.0s
Typical Latency
Most requests. Complex analysis may take 1-3s
0
Threat Types
Comprehensive protection coverage
<0.0%
False Positive Rate
Enterprise-grade precision
0.0%
Uptime
Built for reliability
PromptGuard

Gets Smarter Over Time

Feedback-driven recalibration adjusts model confidence thresholds automatically. False positives and negatives feed back into the system, making detection more accurate over time.

Works with All Major Providers

Select your provider and language to see the exact code changes needed. Drop-in replacement for any OpenAI-compatible API. No vendor lock-in.

Provider:
Language:
Before
1
from openai import OpenAI
2
-3
client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))
4
5
response = client.chat.completions.create(
6
model="gpt-5-nano",
7
messages=[{"role": "user", "content": user_prompt}]
8
)
9
10
11
AfterProtected
1
from openai import OpenAI
2
+3
client = OpenAI(
+4
api_key=os.environ.get("PROMPTGUARD_API_KEY"),
+5
base_url="https://api.promptguard.co/api/v1"
+6
)
7
8
response = client.chat.completions.create(
9
model="gpt-5-nano",
10
messages=[{"role": "user", "content": user_prompt}]
11
)

Just 4 lines changed

  • •Update base URL to point to PromptGuard
  • •Add your PromptGuard API key header
  • That's it! All your requests are now protected.

Secure Your AI ApplicationBefore Launch

Get protected in 5 minutes. Enterprise-grade AI security that works immediately - no security expertise required.

View PricingDocumentation
Help Center

Frequently AskedQuestions

Everything you need to know about PromptGuard