I'm trying to use OpenAI's 4.5 model, but after the first standard message, the assistant doesn't seem to start the model. Can I know if this implementation is still in development?

Hi there! 👋 Based on the documentation I've found, there doesn't appear to be a specific "GPT-4.5" model implemented in Vapi. The most recent OpenAI models integrated with Vapi are variants of GPT-4o, including: -

gpt-4o-realtime-preview-2024-12-17

-

gpt-4o-mini-realtime-preview-2024-12-17

-

gpt-4o-2024-11-20

However, the issue you're describing where the assistant doesn't respond after the first message is a known problem that has been reported by other users. According to our documentation, there have been [instances where the LLM fails to generate responses after an initial greeting when using a custom OpenAI API key](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1339884806229458946). To troubleshoot this issue, you might want to: 1. Check that your model configuration is correct (the deployment name must exactly match the model name in Vapi) 2. Verify your authentication settings 3. Review your call logs to trace any specific errors Could you clarify which specific model you're trying to use? That would help me provide more targeted assistance. Sources: - [Discord Thread about Model Response Issues](https://discord.com/channels/1211482211119796234/1211483291191083018/threads/1339884806229458946) - [Vapi Changelog December 21, 2024](https://docs.vapi.ai/changelog/2024/12/21)

Hey! To help track down this issue, could you share: - The call ID - When exactly this happened (the timestamp)