Add an AI model
Register an AI model your team can reuse across every agent, and validate its credentials.
An agent needs a model to run on. Models are registered once per workspace and then reused everywhere, so credentials live in one place.
Add the model
- In the workspace sidebar, open Models & tools → AI Models.
- Click Add model.
- Enter a name your team will recognise (e.g.
gpt-4o-eu). - Choose a provider — OpenAI, Azure, Anthropic, Google, AWS, Hugging Face, or Cohere.
- Enter the provider's model ID (for example
gpt-4oorclaude-3-5-sonnet). - Pick an authentication strategy (API key, IAM, service account, or OAuth) and fill in the credentials it requires.
- Leave the model type as chat, make sure it is active, and save.
Validate it
From the models list, use the row action Test model to confirm the credentials work before an agent depends on it.
Tip: Credentials are stored securely and never returned to the browser. If Test model fails, re-check the model ID and the auth values with your provider.
Related
- Create an agent — put the model to work.
- Getting started — the full first-agent path.