How to Use the Prompt Endpoint in Vultr Serverless Inference

Updated on September 25, 2024

Vultr Serverless Inference prompt endpoint allows users to send a single prompt to an AI model for generating responses. This service supports interactive and dynamic AI interactions, enabling users to obtain specific outputs based on their prompts and integrate these responses into their applications effectively. By using this feature, you can enhance your application's responsiveness and adaptability to user inputs, providing more personalized and relevant outputs.

Follow this guide to utilize the prompt endpoint on your Vultr account using the Vultr Customer Portal.

  • Vultr Customer Portal
  1. Navigate to Products, click Serverless, and then click Inference.

    Serverless Inference option in products menu

  2. Click your target inference service to open its management page.

    Selection of a target serverless inference service

  3. Open the Prompt page.

    Button to open the prompt endpoint page

  4. Select a preferred model.

    Button to select a preferred embeddings generation model

  5. Provide values of Max Tokens, Seed, Temperature, Top-k and Top-p.

    Fields to provide parameters for the model

  6. Provide a prompt and click on Prompt

    Field to provide a prompt for the model

  7. Click Reset to provide a new prompt.

    Button to reset the prompt field to provide a new prompt