Sending prompt and message using GenAI LLM Passthrough endpoints

1. Use these endpoints to send either a single prompt (/prompt or /prompt/stream) or multiple messages (/messages or /messages/stream):
   • api/v1/prompt
   • api/v1/messages
   • api/v1/prompt/stream
   • api/v1/messages/stream
   • api/v2/messages
   • api/v2/messages/stream
2. Complete the request body with properties from GET/api/v1/models to specify the model and its version.

Ensure that these requirements are met:

• A valid Infor Registry logical ID header is required to invoke the endpoints. Failure to provide a valid header value results in an invocation error.
• You can only select a single model at the time. If a model and version is not selected, the endpoint selects Claude 3 Haiku by default.

For reference, review these sample payloads:

• /prompt and /prompt/streaming API

  {
    "model": "CLAUDE",
    "version": "claude-3-haiku-20240307-v1:0",
    "prompt": "Hello world!"
  }
  

• v1/messages and v1/messages/streaming API

  {
      "system": "You are a math professor, you help people answer math questions.",
      "model": "CLAUDE",
      "version": "claude-3-7-sonnet-20250219-v1:0",  
      "messages": [
          {
              "role": "user",
              "content": [
                  {
                      "type": "text",
                      "data": "What is your favorite algorithm?"
                  },
                  {
                      "type": "text",
                      "data": "Can you tell me yours first?."
                  }
              ]
          },
          {
              "role": "assistant",
              "content": [
                  {
                      "type": "text",
                      "data": "Can you tell me yours first?."
                  }
              ]
          },
          {
              "role": "user",
              "content": [
                  {
                      "type": "text",
                      "data": "But I asked first"
                  }
              ]
          }
      ]
  } 
  
  

• v2/messages and v2/messages/streaming

  o	{
    "modelId": "claude-sonnet-4-20250514-v1: 0",
    "system": "You are Claude, an AI assistant made by Anthropic. You are helpful, harmless, and honest. Be concise, warm, and professional in your responses.",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "Summarize the key responsibilities of a Procurement Manager in 3 bullet points."
          }
        ]
      }
    ]
  }
  

Where:

• Model parameter inside /prompt, v1/messages and v1/messages/streaming is the Name parameter in the GET/api/v1/models
• Version parameter inside /prompt, v1/messages and v1/messages/streaming is the ID parameter in the GET/api/v1/models
• Model ID inside v2/messages and v2/messages/streaming is the ID parameter in the GET/api/v1/models.