Our products scale with you

Red Teaming

Entry

Entry-level Red Teaming suite for AI requiring basic AI security evaluation with basic threat modeling.

14 Attack Strategies
15 Risk Topics
2,100 Total Data Points
Single Turn Attack
Entry Vulnerability Report
Safety System Prompt Guideline
Basic Attack Chains
Customizable / Limited AI Red Teaming tool

Professional

Professional Red Teaming suite for AI requiring intermediate AI security evaluation with advanced threat modeling.

18 Single Attack Strategies
20 Single Risk Topics
Single-Turn Attack (7,200)
Multi-Turn Attack (1,800)
9,000 Total Data Points
Pilot Vulnerability Report
Safety System Prompt Consulting
Advanced Attack Chains
Customizable / Advanced AI Red Teaming tool
Dedicated Contact Point

Enterprise

Enterprise-level Red Teaming suite providing complete AI security evaluation with custom-optimized threat modeling for your production AI.

Unlimited Attack Strategies (30 + ⍺)
Unlimited Risk Topics (30 + ⍺)
Optimized Topics & Strategies
Single Turn Attack (27,000 + ⍺)
Multi-Turn Attack (6,300 + ⍺)
33,300 + ⍺ Total Data Points
Production Vulnerability Report
Safety System Prompt Consulting
Optimized Attack Chains
Customizable / Full AI Red Teaming tool
Dedicated Contact Point
AI Safety Certification Mark Consulting

Entry

Customizable AI Red Teaming tool
- Single Turn Attack
Vulnerability Report
- Format (Structured)
Attack Chains
- Static Data Attack
- Attack Types (text)
Contact
- Slack (Community)

Professional

Customizable AI Red Teaming tool
- Single Turn Attack
- Multi-Turn Attack
- Storage
Vulnerability Report
- Format (Structured)
Attack Chains
- Static Data Attack
- Auto-Generated Attack
- Attack Types (text, image)
Contact
- Slack (Connect)

Enterprise

Customizable AI Red Teaming tool
- Single Turn Attack
- Multi-Turn Attack
- Multi-modal Attack
- Storage
Vulnerability Report
- Format (Customizable)
Attack Chains
- Static Data Attack
- Auto-Generated Attack
- Advanced Attack
- Attack Types (text, image, audio, video)
Contact
- Slack (Dedicated agent)
- Enterprise Integration Support (Priority)

Pricing plan comparison
Compare Features	Entry	Professional	Enterprise
Customizable AI Red Teaming tool
Single Turn Attack	Included in Entry	Included in Professional	Included in Enterprise
Multi-Turn Attack	Not included in Entry	Included in Professional	Included in Enterprise
Multi-modal Attack	Not included in Entry	Not included in Professional	Included in Enterprise
Storage	Not included in Entry	Included in Professional	Included in Enterprise
Vulnerability Report
Format	Structured	Structured	Customizable
Attack Chains
Static Data Attack	Included in Entry	Included in Professional	Included in Enterprise
Auto-Generated Attack	Not included in Entry	Included in Professional	Included in Enterprise
Advanced Attack	Not included in Entry	Not included in Professional	Included in Enterprise
Attack Types	text	text, image	text, image, audio, video
Contact
Slack	Community	Connect	Dedicated agent
Enterprise Integration Support	Not included in Entry	Not included in Professional	Priority
Link to activate plan	Contact Sales	Contact Sales	Contact Sales

Guardrail

Entry

Entry-level AI Guardrail suite for establishing basic AI safety controls and protection mechanisms.

99% Protection Against Entry Red Teaming
Fundamental Safety Chain
Real-time Threat Detection
Core Value Alignment
Monitoring & Control Tool
Entry Safety Report
Dedicated Safety Team
Custom Implementation

Professional

Professional AI Guardrail suite for comprehensive AI safety controls with advanced protection features.

99.9% Protection Against Professional Red Teaming
Advanced Safety Boundaries
Real-time Threat Detection
Dynamic Value Alignment
Monitoring & Control Tool
Advanced Safety Report
Dedicated Safety Team
Custom Implementation

Enterprise

Enterprise-level AI Guardrail suite providing military-grade AI safety controls with custom-optimized protection for your production AI.

99.99% Protection Against Enterprise Red Teaming
Optimized Safety Boundaries
Real-time Threat Detection
Adaptive Value Alignment
Monitoring & Control Tool
Enterprise Safety Report
Dedicated Safety Team
Custom Implementation

Entry

Safety Chain
- Input AI Filter
Value Alignment
Safety Report
- Format (Structured)
Contact
- Slack (Connect)

Professional

Safety Chain
- Input AI Filter
- Output AI Filter
- Filter Assistant
Value Alignment
- Acceptable Custom Safety Polices (100 ~ 150)
Safety Report
- Format (Structured)
Contact
- Slack (Dedicated agent)

Enterprise

Safety Chain
- Input AI Filter
- Output AI Filter
- Filter Assistant
- Auto-Upgrade
Value Alignment
- Acceptable Custom Safety Polices (Unlimited)
Safety Report
- Format (Customizable)
Contact
- Slack (Dedicated agent)
- Enterprise Integration Support (Priority)

Pricing plan comparison
Compare Features	Entry	Professional	Enterprise
Safety Chain
Input AI Filter	Included in Entry	Included in Professional	Included in Enterprise
Output AI Filter	Not included in Entry	Included in Professional	Included in Enterprise
Filter Assistant	Not included in Entry	Included in Professional	Included in Enterprise
Auto-Upgrade	Not included in Entry	Not included in Professional	Included in Enterprise
Value Alignment
Acceptable Custom Safety Polices	Not included in Entry	100 ~ 150	Unlimited
Safety Report
Format	Structured	Structured	Customizable
Contact
Slack	Connect	Dedicated agent	Dedicated agent
Enterprise Integration Support	Not included in Entry	Not included in Professional	Priority
Link to activate plan	Contact Sales	Contact Sales	Contact Sales

Frequently Asked Questions

Can't find the answer you're looking for? Don't hesitate to get in touch with our team.

Our products scale with you

Entry

Professional

Enterprise

Entry

Customizable AI Red Teaming tool

Vulnerability Report

Attack Chains

Contact

Professional

Customizable AI Red Teaming tool

Vulnerability Report

Attack Chains

Contact

Enterprise

Customizable AI Red Teaming tool

Vulnerability Report

Attack Chains

Contact

Entry

Professional

Enterprise

Entry

Safety Chain

Value Alignment

Safety Report

Contact

Professional

Safety Chain

Value Alignment

Safety Report

Contact

Enterprise

Safety Chain

Value Alignment

Safety Report

Contact

Frequently Asked Questions

What is the difference between Red Teaming and Guardrail?

How long does it take to implement these solutions?

Can I use it as on-premises or SaaS?

Can classification criteria be customized?

What is the difference between Pre-Fix and Quick-Fix?

Does it provide security for output values?

Is API integration available?

Can masking patterns be customized?

How are harmful content patterns updated?

How can I manually update rules?

Is offline update supported?

Can latency be monitored?

When should I use red teaming site?

How are output values analyzed?

Can it detect anomalies in output messages?

What data is provided for red teaming tracing?

Is tracing automated?

What is the licensing policy?

Are there user or usage limits?

What level of API integration is supported?

Can the interface be customized?

What are the VM resource requirements?

How is PoC conducted?

Is on-premise deployment supported?

Can it integrate with VPN?

What is the typical project duration?

Product

Resources

Company