Help
AI Providers
Nebo works with multiple AI providers. You choose which model powers your assistant.
Supported Providers
| Provider | Models | API Key Required |
|---|---|---|
| Anthropic | Claude 4, Claude 3.5 | Yes |
| OpenAI | GPT-4o, GPT-4 | Yes |
| Google Gemini | Gemini Pro, Flash | Yes |
| Ollama | Llama, Mistral, etc. | No (runs locally) |
| DeepSeek | DeepSeek V3 | Yes |
Configuration
Via the UI
Go to Settings > Providers in the Nebo web interface. Enter your API key and select your preferred model.
Via Configuration File
Edit models.yaml in your Nebo data directory:
- macOS:
~/Library/Application Support/nebo/models.yaml - Linux:
~/.local/share/nebo/models.yaml - Windows:
%APPDATA%/nebo/models.yaml
Running Offline with Ollama
Install Ollama from ollama.ai, pull a model, and Nebo detects it automatically:
ollama pull llama3.2
No API key, no internet connection required. All processing happens on your machine.
Switching Providers
You can switch providers at any time. Your conversation history, memory, and installed extensions work with any provider.