How to Use the Chat Endpoint in Vultr Serverless Inference

1 min readUpdated 4 November 2026

Chat with LLMs on Vultr Serverless Inference, with tool calling so models can invoke functions, via Console or API.

The Vultr Serverless Inference chat endpoint lets you hold real-time conversations with Large Language Models (LLMs). The endpoint also supports tool calling, which lets models invoke functions that you define, such as fetching live data or calling an API, during a conversation. You can integrate the endpoint into your applications to add conversational AI features.

Follow this guide to use the chat endpoint on your Vultr account using the Vultr Console or API.

Navigate to Compute and click Serverless Inference.
Click the target subscription to open its Manage Serverless Inference page.
Click the Chat tab.
Click the Select Model drop-down and select a model.
Enter a value in Max Tokens.
Enter a message in the Message Vultr Chat field and click the Send icon.
Optionally, expand Thinking in a response to view the model's reasoning.
Optionally, expand History to view previous conversations.
Click New Conversation to start a new chat.

0 Comments

Start the conversation

Be the first to comment and share your perspective with the community.

Use the Chat Endpoint in Vultr Serverless Inference | Vultr Docs