@Swarnim007 Hello! I'd be happy to assist you with integrating your fine-tuned GPT-3.5 Turbo model into VAPI as a Custom LLM. Here's a step-by-step guide to help you set it up: 1. **Log in to your VAPI account**: Start by logging into your VAPI dashboard. 2. **Navigate to the Model Section**: Once you're in, head over to the "Model" section of the dashboard. 3. **Select Custom LLM**: In the Model section, you should see an option to choose a "Custom LLM". Select this to begin the integration process. 4. **Set API Key in Provider Credentials**: You'll need to enter the API key from your OpenAI account. Make sure you're using the correct key that has permissions to access your fine-tuned model. 5. **Replace the Model Name**: In the configuration, replace the default model name with the name of your fine-tuned GPT-3.5 Turbo model. The model name should be exactly as it appears in your OpenAI account. 6. **Save Changes**: After you've entered the API key and model name, save the changes to apply the configuration. If you've followed these steps and it's still not working, there might be an issue with the API key permissions, the model name, or another configuration setting. Double-check that all the information you've entered is correct and that your fine-tuned model is accessible with the API key you've provided. If you continue to face issues, it might be best to reach out to VAPI support directly for more personalized assistance. They can provide more detailed troubleshooting based on the specifics of your account and model. Remember, it's important to ensure that your API key is kept secure and not shared with anyone who should not have access to your OpenAI models. If you need further assistance or have any more questions, feel free to ask!

Got it. Tagging @User for additional help.

Got it. Tagging @User for additional help.

Use this

this will solve your issue

also read custom-llm doc