Skip to main content

AI Providers

Configure which AI provider KubeAgentiX uses for natural language queries.

Default Provider​

Plus and Enterprise subscriptions include credits for Google's Gemini 2.5 Flash model. No configuration needed - it works out of the box.

Bring Your Own Key (BYOK)​

All plans support using your own API keys.

OpenAI​

  1. Get an API key from platform.openai.com
  2. Go to Settings → AI Provider
  3. Select OpenAI
  4. Enter your API key
  5. Choose a model (GPT-4 recommended)

Anthropic​

  1. Get an API key from console.anthropic.com
  2. Go to Settings → AI Provider
  3. Select Anthropic
  4. Enter your API key
  5. Choose a model (Claude 3.5 Sonnet recommended)

Google Vertex AI​

  1. Create a GCP project with Vertex AI enabled
  2. Create a service account with Vertex AI User role
  3. Download the JSON key file
  4. Go to Settings → AI Provider
  5. Select Vertex AI
  6. Upload the service account key

Local Models (Ollama)​

For fully offline operation:

  1. Install Ollama
  2. Pull a model: ollama pull llama3
  3. Go to Settings → AI Provider
  4. Select Ollama
  5. Choose your model
Use CaseProviderModel
Best qualityAnthropicClaude 3.5 Sonnet
Fast responsesGoogleGemini 2.5 Flash
Cost-effectiveOpenAIGPT-4o-mini
Privacy-focusedOllamaLlama 3 70B

API Key Security​

Your API keys are:

  • Stored locally in your system's secure keychain
  • Never sent to KubeAgentiX servers
  • Only used for direct API calls to the provider