I have fine-tuned my model with the base model “gpt-4o-mini-2024-07-18”
When I paste my fine-tuned model’s ID “ft:gpt-4o-mini-2024-07-18:personal::my-model” into my script and run it, I receive this error:
Received event: error {‘type’: ‘error’, ‘event_id’: ‘event_AZ41zc4vaNKToBrwEyBYt’, ‘error’: {‘type’: ‘invalid_request_error’, ‘code’: None, ‘message’: “Model ft:gpt-4o-mini-2024-07-18:personal::my-model cannot be used with this API. Please use one of [‘gpt-4o-realtime-preview-2024-10-01’, ‘gpt-4o-realtime-preview’]”, ‘param’: None, ‘event_id’: None}}
When I use “gpt-4o-realtime-preview-2024-10-01” it works.
The line of code I’m inserting my model ID into is: “wss://api.openai.com/v1/realtime?model=”
Are custom models not supported by the realtime endpoint? If they are, how can I call on my fine-tuned model?