Skip to main content
Model connections define how agents access AI providers. Each connection maps a model ID to a specific provider and authentication method.
Set up credentials before configuring model connections.

​
Managing via UI

Navigate to Configuration → Model Connections in the AgentSystems UI at http://localhost:3001. The UI allows you to:
  • Add connections to AI providers
  • Enable/disable connections

​
Supported Models

Model IDDisplay NameProvidersRequired Credentials
gpt-4oGPT-4oOpenAIOPENAI_API_KEY
gpt-4o-miniGPT-4o miniOpenAIOPENAI_API_KEY
claude-3-5-sonnetClaude 3.5 SonnetAnthropic, AWS BedrockANTHROPIC_API_KEY or AWS credentials
claude-3-5-haikuClaude 3.5 HaikuAnthropic, AWS BedrockANTHROPIC_API_KEY or AWS credentials
llama3.1:8bLlama 3.1 8BOllama, AWS BedrockNone (Ollama) or AWS credentials
gemma3:1bGemma 3 1BOllamaNone (local)
nova-proAmazon Nova ProAWS BedrockAWS credentials
For the full list of supported models, check the Model Connections page in the UI at http://localhost:3001.

​
Configuration Structure

Each model connection requires:
FieldDescriptionRequired
hosting_providerProvider name (openai, anthropic, amazon_bedrock, ollama)Yes
hosting_provider_model_idProvider-specific model identifierYes
enabledWhether this connection is activeYes
authAuthentication configurationYes
hosting_provider_base_urlCustom endpoint (Ollama only)No
hosting_provider_regionAWS region (Bedrock only)No

​
Manual Configuration

Edit agentsystems-config.yml directly: 
config_version: 1

model_connections:
  # Give each connection a unique ID
  my-gpt4-connection:
    hosting_provider: openai
    hosting_provider_model_id: gpt-4
    enabled: true
    auth:
      method: api_key
      api_key_env: OPENAI_API_KEY

  my-claude-connection:
    hosting_provider: anthropic
    hosting_provider_model_id: claude-3-opus-20240229
    enabled: true
    auth:
      method: api_key
      api_key_env: ANTHROPIC_API_KEY
After editing, restart the platform: 
agentsystems restart
⌘I