Skip to main content
🚀 Start Free - 1,000 requests/month

The Firewall for AI Prompts

PromptGuard is the security layer between your application and your LLM, ensuring every interaction is safe, compliant, and fully logged. One URL change delivers end-to-end prompt governance at scale.

Works with all LLM providers
5-minute setup
Minimal code changes
Simple Integration

How it works

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

1

Change your base URL

Instant Setup

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

2

Configure security rules

Flexible Policies

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

3

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
<40ms overhead
main.py
1
from openai import OpenAI
2
3
client = OpenAI(
4
base_url="https://api.promptguard.co/api/v1",
5
api_key=os.environ["OPENAI_API_KEY"],
6
default_headers={"X-API-Key": os.environ["PROMPTGUARD_API_KEY"]},
7
)
That's it. Requests are now protected.
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

Click an example to test:

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

Enterprise-Grade Security

Complete Protection forYour AI Applications

Drop-in security that scales with your application. Works with all LLM providers. No vendor lock-in.

Complete AI Security

Protect against prompt injection, PII leaks, data exfiltration, toxicity, fraud, and malware. AI-powered detection with ~95% accuracy.

AI-Powered Detection

Advanced machine learning models catch sophisticated attacks that regex patterns miss. ~95% accuracy with <40ms latency overhead. Gets smarter over time - every attack we see makes detection more accurate for everyone.

Data Leak Prevention

Automatically detect and redact PII, secrets, API keys, and sensitive information before it reaches your LLM.

Works Immediately

Protect your app in 5 minutes. Change your base URL and add an API key - that's it. Works from the first request. No security expertise needed.

Works Everywhere

Compatible with OpenAI, Claude, Gemini, Groq, Azure, and any OpenAI-compatible API. No vendor lock-in. Handles any volume with <40ms overhead.

Zero Retention Mode

Your data stays private. Option to process requests without storing any content.

Verified Performance

Production-Ready Security

Real benchmarks. Measured performance. Built for scale.

<0ms
Latency Overhead
Measured on AWS t3.medium instances
~0%
Detection Accuracy
AI-powered threat detection
ZERO
False Positives
Production-tested precision
0.0
Uptime
Built for reliability
PromptGuard

Gets Smarter Over Time

Our threat database grows daily from real attacks, making detection more accurate over time. Every attack we see improves protection for everyone.

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-4",
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-4",
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.

Choose Your Plan

Start free, scale as you grow. No hidden fees, cancel anytime.

Free

Try PromptGuard with 1K requests

$0/month
  • 1,000 API requests per month
  • Basic security (70-80% accuracy)
  • Prompt injection & PII detection
  • 24-hour log retention
  • Free CLI & VS Code Extension
  • Community support
  • Upgrade to Starter for AI-powered security
Most Popular

Starter

Production-ready with ML security

$49/month
  • 100,000 API requests per month
  • AI-powered security (~95% accuracy)
  • All threat types: injection, PII, exfiltration, toxicity, fraud
  • Email alerts for threats
  • 7-day log retention
  • Email support
  • Best for production apps

Growth

Built for scale. Never blocks your users.

$149/month
  • 1M requests/month (soft limit)
  • AI-powered detection (~95% accuracy)
  • Advanced analytics dashboard
  • Priority support (24hr SLA)
  • 30-day log retention
  • Everything in Starter, plus uptime guarantees

Need more than 1M requests/month? Contact us for Enterprise Pricing

Protect Your AI App
Before Launch

Get protected in 5 minutes. AI-powered security that works immediately. No security expertise needed.

Read the Docs
Help Center

Frequently AskedQuestions

Everything you need to know about PromptGuard