Thank you for the insight. I made your recommended modifications; they appear to have worked, but I am getting a new error:
ERROR Chat Model Prompter 4:1767:0:1765 Execute failed: Error code: 400 - {‘error’: {‘message’: “Unsupported parameter: ‘max_tokens’ is not supported with this model. Use ‘max_completion_tokens’ instead.”, ‘type’: ‘invalid_request_error’, ‘param’: ‘max_tokens’, ‘code’: ‘unsupported_parameter’}}
The max_tokens parameter in the current OpenAI Chat Model Connector node is/cannot be converted in any way to the new parameter max_completion_tokens, so I assume this is a dead end for this node with the gpt-1o model. Will try to configure my chatbot for the 1o model using the nodepit OpenAI nodes, which presumably allow this level of configuration in the JSON string.