Gemini 3.5 Flash-Lite

Google Gemini API · type: "gemini"

Model ids: gemini-3.5-flash-lite

1. Store the credential

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

${vault:gemini-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": "gemini",
      "parameters": {
        "apiKey": "${vault:gemini-key}",
        "modelName": "gemini-3.5-flash-lite",
        "maxOutputTokens": "8192",
        "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 gemini-3.5-flash-lite agent",
  systemPrompt: "You are a helpful assistant.",
  provider: "gemini",
  model: "gemini-3.5-flash-lite",
  apiKey: "${vault:gemini-key}"
)

Google Vertex AI · type: "gemini-vertex"

Model ids: gemini-3.5-flash-lite

1. Store the credential

This provider does not use an API key: Vertex AI authenticates with Google Application Default Credentials. Set projectId and location for your project.

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": "gemini-vertex",
      "parameters": {
        "projectId": "your-gcp-project",
        "location": "us-central1",
        "modelId": "gemini-3.5-flash-lite",
        "systemMessage": "You are a helpful assistant",
        "addToOutput": "true"
      }
    }
  ]
}