Skip to main content
In self-hosted mode, kombify AI uses your own API keys to access AI models. This guide covers how to set up and manage your keys securely.

​
Supported providers

ProviderModelsSetup
OpenAIGPT-4o, GPT-5-nanoAPI key from platform.openai.com
AnthropicClaude Sonnet, Claude HaikuAPI key from console.anthropic.com
Google AIGemini Pro, Gemini FlashAPI key from aistudio.google.com
Azure AI FoundryHosted modelsEndpoint + API key
OpenRouter200+ modelsAPI key from openrouter.ai
OllamaSelf-hosted modelsLocal endpoint (no key needed)

​
Adding API keys

1

Open the AI portal

Navigate to your kombify AI portal (default: http://your-server:5270).
2

Go to Settings > API Keys

Each provider has its own section with fields for the required credentials.
3

Enter your key

Paste your API key. It is encrypted with AES-256-GCM before storage.
4

Test the connection

Click “Test” to verify the key works and the provider is reachable.

​
Security

  • All keys are encrypted at rest with AES-256-GCM
  • Keys never leave your server
  • No key data is sent to kombify servers
  • Keys are stored in the local database (SQLite in self-hosted mode)

​
Cost management

kombify AI tracks token usage and estimated costs per request. View your spending in AI Settings > Usage.
Set monthly budget alerts to avoid unexpected costs. kombify AI defaults to cost-efficient models for simple tasks.

​
Further reading

Supported models

Full list of supported models per provider

Configuration reference

All AI configuration options