Configure your AI models
At a glance
Ontologie lets you connect your own language models (LLMs) to power AI agents and AI blocks in workflows. Bring your own API key (BYO-key) to use the provider of your choice.
Before you begin
- Be an administrator of the workspace
- Have a valid API key from an LLM provider
Supported providers
| Provider | Common models |
|---|---|
| Anthropic | Claude Sonnet, Claude Opus, Claude Haiku |
| OpenAI | GPT-4o, GPT-4o mini |
| Gemini Pro, Gemini Flash | |
| Mistral | Mistral Large, Mistral Small |
| Groq | Llama, Mixtral (fast inference) |
| Cohere | Command R, Command R+ |
| Local model | Any OpenAI API-compatible model (e.g. Ollama, vLLM) |
Adding a provider
- Go to Workspace settings > AI Models.
- Click + Add a provider.
- Select the provider from the list.
- Enter your API key.
- Click Test connection to verify.
- Click Save.
info
Your API key is encrypted at rest and is never exposed in the interface after saving.
Local model (OpenAI API-compatible)
To use a model hosted locally or on your own infrastructure:
- Select Local model as the provider.
- Enter your API URL (e.g.
http://localhost:11434/v1). - Enter the model name (e.g.
llama3.1:8b). - Optional: enter an API key if your server requires one.
- Test and save.
Configuring the default model
- In the providers list, click the model you want to set as default.
- Click Set as default model.
The default model is used by:
- New agents created in Agent Studio
- AI blocks in workflows (unless specifically configured otherwise)
- Natural language queries in spreadsheets
Choosing a model per agent
Each agent can use a different model:
- Open the agent in Agent Studio.
- Go to the Configuration tab.
- In the Model section, select the desired provider and model.
This lets you use a fast model for simple agents and a more powerful model for complex tasks.
Key security
| Practice | Description |
|---|---|
| Encryption | Keys are encrypted at rest (AES-256) |
| Restricted access | Only administrators can view and modify providers |
| Rotation | Update your keys regularly — the old key is replaced immediately |
| Audit | Every LLM call is traced in the workspace logs |
Troubleshooting
| Problem | Cause | Solution |
|---|---|---|
| "Invalid key" | Incorrect or expired API key | Verify the key on the provider's website |
| "Model not found" | Incorrect model name | Verify the exact model name in the provider's documentation |
| "Timeout" | The provider is not responding | Check the provider's availability |
| "Quota exceeded" | Provider quota exhausted | Check your usage on the provider's dashboard |
See also
- Agent Studio — Create AI agents
- Account settings — Profile and preferences
- Workspace management — Roles and access
Need help?
Contact us: Support and contact.