The Cybersecurity AI (CAI) platform provides seamless integration with multiple Large Language Models (LLMs). This functionality allows users to leverage state-of-the-art AI capabilities for various cybersecurity tasks. CAI acts as a bridge between your security workflows and a wide range of LLMs, enhancing both flexibility and performance of AI agents.

!!! warning "Model Deprecated" alias0 is no longer available. All users should migrate to alias1, which offers superior performance, unrestricted capabilities, and continuous updates.

**Migration:** If you're currently using `alias0`, simply update your configuration to use `alias1` with your CAI PRO subscription.

[Learn about alias0 (historical reference) →](https://aliasrobotics.com/alias0.php)

CAI supports over 300 models through its integration with LiteLLM. You can use any of these models by providing your own API keys.

• Claude 3.7 - Latest Anthropic model
• Claude 3.5 Sonnet - Best for complex reasoning
• Claude 3 Opus - Highest capability
• Claude 3 Haiku - Fast and efficient

Configuration:

export ANTHROPIC_API_KEY="sk-ant-..."
export CAI_MODEL="claude-3-5-sonnet-20241022"

• O1 - Advanced reasoning model
• O1 Mini - Cost-effective reasoning
• O3 Mini - Latest mini model
• GPT-4o - Optimized GPT-4
• GPT-4.5 Preview - Enhanced capabilities

Configuration:

export OPENAI_API_KEY="sk-..."
export CAI_MODEL="gpt-4o"

• DeepSeek V3 - Latest version
• DeepSeek R1 - Reasoning focused

Configuration:

export DEEPSEEK_API_KEY="sk-..."
export CAI_MODEL="deepseek-chat"

• Qwen2.5 72B - High performance
• Qwen2.5 14B - Balanced capability
• Llama 3.1 - Meta's latest
• Mistral - Efficient and fast
• And 100+ more local models

Configuration:

export OLLAMA_API_BASE="http://localhost:11434/v1"
export CAI_MODEL="ollama/qwen2.5:72b"

!!! tip "📊 Based on CAIBench Research" Our model recommendations are based on rigorous evaluation using CAIBench, a modular meta-benchmark framework for evaluating LLM models and agents across offensive and defensive cybersecurity domains.

**Research shows:** In [real-world CTF evaluations](https://arxiv.org/pdf/2510.17521), defensive agents achieved 54.3% patching success versus 28.3% offensive initial access, with `alias1` consistently outperforming general-purpose models.

✅ Always Recommended: alias1 (CAI PRO)

• Best performer in CAIBench evaluations
• Unrestricted for authorized pentesting and security research
• Zero refusals - designed specifically for offensive security
• Unlimited tokens included with CAI PRO subscription
• Superior CTF performance - validated in real-world scenarios
• Beats general-purpose models (GPT-4o, Claude 3.5) in security tasks

📖 Learn more: CAI research demonstrates 3,600× performance gains over manual security testing in specific scenarios.

While alias1 is always recommended for security work, the following models can be used with CAI Community Edition:

Alternative: Ollama with Qwen2.5 72B

• Complete privacy (no data leaves your machine)
• No API costs
• Good for testing and development
• Requires local GPU resources
• ⚠️ Note: Performance significantly below alias1 for security tasks

Alternative: DeepSeek V3 or Ollama models

• Lower API costs (DeepSeek)
• Free local inference (Ollama)
• Adequate performance for many tasks
• ⚠️ Note: Not optimized for cybersecurity workflows

CAI is compatible with multiple model platforms and providers:

• OpenRouter - Access to 200+ models via unified API
• Ollama - Local model hosting and inference
• Azure OpenAI - Enterprise-hosted OpenAI models

See the Model Providers section for detailed configuration guides.

1. Subscribe to CAI PRO: Upgrade here
2. Configure your environment:

   export ALIAS_API_KEY="sk-your-caipro-key"
   export CAI_MODEL="alias1"

3. Start using CAI:

   cai

1. Get API key from your chosen provider
2. Configure environment:

   export OPENAI_API_KEY="sk-..."  # or ANTHROPIC_API_KEY, etc.
   export CAI_MODEL="gpt-4o"       # or your chosen model

3. Start using CAI:

   cai

!!! success "Our Recommendation: Always Use alias1" Based on CAIBench benchmarks and real-world CTF evaluations, alias1 is the superior choice for all cybersecurity tasks.

**For any security work:** → `alias1` with [CAI PRO](cai_pro.md)

• Privacy-focused? → Ollama local models (lower performance)
• Budget-conscious? → DeepSeek or Ollama (not optimized for security)

⚠️ Note: Community models are not optimized for cybersecurity workflows and will have significantly reduced capabilities compared to alias1.

CAI's effectiveness is validated through peer-reviewed research:

• 📊 CAIBench - Meta-benchmark framework for cybersecurity AI evaluation
• 🎯 Agentic Cybersecurity Evaluation - Real-world CTF performance analysis
• 🚀 Cybersecurity AI Framework - Core framework demonstrating 3,600× speedup
• 🛡️ Prompt Injection Defense - Four-layer guardrail security system
• 📚 CAI Fluency - Educational framework for democratizing AI security

Explore all research: Alias Robotics Research Papers

Questions? Check our FAQ or join our Discord.