GPT-6 (Astra, Sol, Luna)

OpenAI · type: "openai"

Model ids: gpt-6.1-sol, gpt-6-astra, gpt-6-luna

1. Store the credential

Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/openai-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.

${vault:openai-key}

2. Configure the LLM task

Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.

{
  "tasks": [
    {
      "actions": [
        "send_message"
      ],
      "id": "chat",
      "type": "openai",
      "parameters": {
        "apiKey": "${vault:openai-key}",
        "modelName": "gpt-6.1-sol",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}

Or create the whole agent in one call

setup_agent writes the rules, LLM configuration and workflow, then deploys the agent. Call it over MCP or POST /administration/agents/setup.

setup_agent(
  agentName: "My gpt-6.1-sol agent",
  systemPrompt: "You are a helpful assistant.",
  provider: "openai",
  model: "gpt-6.1-sol",
  apiKey: "${vault:openai-key}"
)

Azure OpenAI · type: "azure-openai"

Model ids: gpt-6-sol

1. Store the credential

Add the provider's API key to the Secrets Vault in the Manager, or with PUT /secretstore/secrets/default/azure-openai-key, under the name used below. Configurations reference it as ${vault:…}, so the key never appears in plain text.

${vault:azure-openai-key}

2. Configure the LLM task

Use this as the langchain.json of the agent's workflow, or paste the parameters into the LLM editor in the Manager.

{
  "tasks": [
    {
      "actions": [
        "send_message"
      ],
      "id": "chat",
      "type": "azure-openai",
      "parameters": {
        "apiKey": "${vault:azure-openai-key}",
        "deploymentName": "gpt-6-sol",
        "endpoint": "https://your-resource.openai.azure.com",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}