Skip to main content
Model Connections tell agents which model to use, where it is hosted, and how to authenticate. Each entry is reusable across multiple agents in your workspace.

​
Adding a model connection

Click Add Model Connection and fill in the form:
FieldDescription
NameA friendly name shown in the agent builder (e.g., “GPT-4o Production”, “Claude Sonnet Production”)
Connection typeWhere the model is hosted — OpenAI, Anthropic, Groq, OpenShift AI, Hugging Face, or Custom endpoint
Model IDThe identifier your provider expects (e.g., gpt-4o, claude-sonnet-4-20250514, meta-llama/Llama-3.1-8B-Instruct)
EndpointShown based on connection type — custom URL for OpenShift or self-hosted servers; optional for Hugging Face dedicated endpoints
CredentialsAPI key stored as a secret in the vault
Studio configures the technical connection for you. You choose where the model lives; agents reference the connection by name.

​
Connection types

Connection typeWhen to useExample Model IDs
OpenAIOpenAI or OpenAI-compatible cloud APIsgpt-4o, gpt-4o-mini
AnthropicClaude modelsclaude-sonnet-4-20250514, claude-3-5-haiku-20241022
GroqGroq-hosted modelsllama-3.3-70b-versatile, mixtral-8x7b-32768
OpenShift AIModels served in your OpenShift clusterllama-3-8b-instruct, mistral-7b-instruct
Hugging FaceDedicated Inference Endpoints or Hub repo IDsmeta-llama/Llama-3.1-8B-Instruct
Custom endpointvLLM, TGI, LM Studio, or other self-hosted serversllama-3, mistral-7b
For local or self-hosted OpenAI-compatible servers (Ollama, vLLM, TGI), choose Custom endpoint and set the full base URL (e.g., http://localhost:11434/v1).

​
Credentials become secrets

When you save a model connection with a new API key, Studio:
  1. Stores the key in the Registry secrets store with a suggested name (e.g., OPENAI_API_KEY, OPENSHIFT_AI_API_KEY)
  2. References the secret in the connection config — the raw key is never stored in plain text
See Secrets for how this works. To rotate a key: Edit the connection and enter a new secret value. All agents using that connection pick up the new key automatically.

​
Endpoint guidance

Connection typeEndpoint behavior
OpenAIDefault endpoint works for api.openai.com; use custom URL only for proxies or gateways
AnthropicEndpoint is configured automatically
GroqDefault Groq endpoint is used automatically
OpenShift AIBase URL of your model’s inference route in the cluster (usually ending in /v1)
Hugging FaceRequired for dedicated Inference Endpoints; leave empty for serverless Hub models using org/model IDs
Custom endpointFull base URL of your server (e.g., http://localhost:11434/v1)

​
Using connections in agents

When creating or editing an agent, select an existing model connection from the inference tab. You do not re-enter credentials — agents inherit authentication from the connection.

​
Next steps

Creating an Agent

Once you have a model connection, you are ready to create your first agent.