OpenAI (GPT)

OpenAI provides GPT-4 and o1 models for security analysis. This guide covers setup and configuration.

Available Models

Authentication

API Key Setup

1. Get your API key from platform.openai.com
2. Run authentication:

cyberstrike auth login
# Select: OpenAI
# Enter your API key

Environment Variable

export OPENAI_API_KEY="sk-proj-..."

Configuration File

{
  "provider": {
    "openai": {
      "options": {
        "apiKey": "{env:OPENAI_API_KEY}"
      }
    }
  }
}

Model Configuration

Set Default Model

{
  "model": "openai/gpt-4o"
}

Command Line Override

cyberstrike --model openai/o1

Using o1 Reasoning Models

o1 models excel at complex security analysis:

cyberstrike --model openai/o1

Best for:

• Complex vulnerability chains
• Attack path analysis
• Cryptographic analysis
• Reverse engineering

ChatGPT Plus/Pro

Use your ChatGPT subscription:

cyberstrike auth login
# Select: OpenAI
# Choose: ChatGPT Plus/Pro
# Complete browser authentication

Organization ID

For organization accounts:

{
  "provider": {
    "openai": {
      "options": {
        "apiKey": "{env:OPENAI_API_KEY}",
        "organization": "org-..."
      }
    }
  }
}

Custom Base URL

For OpenAI-compatible endpoints:

{
  "provider": {
    "openai": {
      "options": {
        "baseURL": "https://your-endpoint.com/v1"
      }
    }
  }
}

Function Calling

GPT models support function calling for tool use:

{
  "provider": {
    "openai": {
      "options": {
        "parallelToolCalls": true
      }
    }
  }
}

Rate Limits

OpenAI rate limits by tier:

Handling Limits

{
  "provider": {
    "openai": {
      "options": {
        "maxRetries": 3,
        "timeout": 60000
      }
    }
  }
}

Best Practices

Model Selection

Cost Optimization

1. Use mini models for simple tasks
2. Set reasonable max tokens
3. Use /compact for long sessions
4. Monitor usage on OpenAI dashboard

Security

1. Store keys in environment variables
2. Use project-specific API keys
3. Enable usage limits in OpenAI dashboard
4. Rotate keys periodically

Troubleshooting

Invalid API Key

Error: Incorrect API key provided

Verify:

• Key starts with sk-proj- or sk-
• No extra whitespace
• Key is active

Insufficient Quota

Error: You exceeded your current quota

Solutions:

• Add billing information
• Check usage limits
• Upgrade your plan

Model Access

Error: The model does not exist or you do not have access

Some models require:

• Tier 3+ for o1
• Waitlist approval
• Enterprise agreement

Related Documentation

• Providers Overview - All providers
• Custom Providers - OpenAI-compatible setup
• Configuration - Full options