Discrepancy in connect Function: model Parameter Usage Differs Between Browser and Server Implementations

[muradsofi]

In the RealtimeAPI class, the connect function accepts a model parameter on the browser side and includes it dynamically in the WebSocket URL. However, on the server side (Node.js), the model seems to be hardcoded as gpt-4o-realtime-preview-2024-10-01 and does not utilize the model argument passed to the function.

It's unclear if this behavior is intentional or an oversight. Could you clarify whether the server-side implementation is designed to always use a static model or if it should also respect the model parameter provided during connection?

---

Steps to Reproduce

1. Examine the connect function in the RealtimeAPI class.
2. On the browser side, the model parameter is appended dynamically to the WebSocket URL:

   const ws = new WebSocket(`${this.url}${model ? `?model=${model}` : ''}`, [ /* protocols */ ]);

3. On the server side, the WebSocket URL has the model hardcoded as:

   const ws = new WebSocket(
       'wss://api.openai.com/v1/realtime?model=gpt-4o-realtime-preview-2024-10-01',
       [],
       { /* options */ }
   );

4. The server-side code does not use the model parameter passed to the connect function.

---

Expected Behavior

The server-side implementation should either:

1. Use the model parameter dynamically as the browser implementation does, or
2. Provide a comment or documentation clarifying that the model is intentionally static on the server side.

---

Actual Behavior

The server-side implementation always uses the hardcoded model gpt-4o-realtime-preview-2024-10-01, ignoring the model parameter.

---

Additional Context

Please confirm if this discrepancy is intentional. If it’s by design, could you clarify the reasoning? If not, should the server-side implementation be updated to dynamically use the model parameter as the browser implementation does?