extended-salmon•4h ago

Custom LLM Inquiry

Hi @Vapi @Vapi Support Bot , I wanted to clarify a few points regarding custom LLM integration with Vapi: 1. Can we use Azure Openai Realtime APIs with a custom LLM ? 2. Is it necessary to create a separate backend API layer to connect the custom LLM, or can we directly use the Azure OpenAI endpoint URL and credentials within the assistant configuration?

1 Reply

Vapi Support Bot•4h ago

You do not need a separate backend API layer—Vapi allows you to connect directly to your Azure OpenAI endpoint using your credentials. Here’s a sample configuration for your assistant:

{
  "provider": "azure-openai",
  "models": ["gpt-4o-2024-11-20"],
  "region": "eastus",
  "openAIEndpoint": "https://your-resource.openai.azure.com",
  "openAIKey": "your-azure-openai-api-key"
}

{
  "provider": "azure-openai",
  "models": ["gpt-4o-2024-11-20"],
  "region": "eastus",
  "openAIEndpoint": "https://your-resource.openai.azure.com",
  "openAIKey": "your-azure-openai-api-key"
}

Just ensure your deployment name matches Vapi’s supported models exactly for a smooth setup.
For more details, see the Vapi Azure OpenAI integration guide. Source: - Azure OpenAI Integration Guide

⤵️ Mention @Vapi Support Bot for follow-ups 🐥

Custom LLM Inquiry

Did you find this page helpful?