Invoke Configuration Page

Select the Anthropic LLM model to use and define the structure of the input request (either a simple prompt or an extended prompt).

Element Description

Anthropic LLM Models

Select the model to use in this integration.

See Models overview.

Request Type

Select the request type to define the structure of the input request:
  • Simple Prompt: Enables you to provide a straightforward instruction or question to the Anthropic LLM model. For example, run the integration with the following text:
    {
      "messages": [{
        "role": "user",
        "content": "What are the GPS co-ordinates for Bengaluru!"
      }]
    }

    The single prompt focuses on clarity and conciseness, avoiding complex phrasing or unnecessary details that can potentially confuse the model.

  • Extended Prompt: Enables you to provide a specific implementation that uses arrays. The following example shows how to specify content as an array element:

    {
        "system": "Give information only about Boston",
        "messages": [
            {
                "role": "user",
                "content": [{"type": "text", "text": "What is the zipcode of Beacon Hill, Boston?"}]
            }
        ]
    }
    Or:
    {
        "system": "You know information only about Boston. Deny information for other places.",
        "messages": [
            {
                "role": "user",
                "content": [{"type": "text", "text": "What is the zipcode of New York?"}]
            }
        ]
    }
    You can call tools and functions. Run the integration with the tools parameter that includes related information about the functions. For example:
    {
      "model": "claude-opus-4-20250514",
      "max_tokens": 1024,
      "tools": "[\n        {\n            \"name\": \"get_weather\",\n            
    \"description\": \"Get the current weather in a given location\",\n            
    \"input_schema\": {\n                \"type\": \"object\",\n                
    \"properties\": {\n                    \"location\": {\n                        
    \"type\": \"string\",\n                        
    \"description\": \"The city and state, e.g. San Francisco, CA\"\n                    },
    \n                    \"unit\": {\n                        \"type\": \"string\",\n                        \"enum\": [\n                            \"celsius\",\n                            \"fahrenheit\"\n                        ],\n                        \"description\": \"The unit of temperature, either 'celsius' or 'fahrenheit'\"\n                    }\n                },\n                \"required\": [\n                    \"location\"\n                ]\n            }\n        },\n        {\n            \"name\": \"get_time\",\n            \"description\": \"Get the current time in a given time zone\",\n            \"input_schema\": {\n                \"type\": \"object\",\n                \"properties\": {\n                    \"timezone\": {\n                        \"type\": \"string\",\n                        \"description\": \"The IANA time zone name, e.g. America/Los_Angeles\"\n                    }\n                },\n                \"required\": [\n                    \"timezone\"\n                ]\n            }\n        }\n    ]",
      "messages": [{
        "role": "user",
        "content": [
          {
            "type": "text","text": "What is the weather like right now in New York? Also what 
    time is it there?"
          }]
      }]
    }

    This framework allows the model to interact with services and perform actions based on your prompt.