Skip to content

Overview

The Verda Inference API offers a suite of endpoints for different machine learning models, enabling you to leverage state-of-the-art technologies in your applications. Our APIs are designed to be robust, scalable, and easy to integrate.

Three things stand between you and your first API response: an account, a funded balance, and a bearer token.

  1. Getting Started — create your Verda account and add funds to your project balance.
  2. Authorization — generate a bearer token under Keys -> Inference API Keys and use it in the Authorization header of every request.
  3. Pick an endpoint from the reference — Language Models, Image Models, or Whisper — and send your first request.

Each reference page includes a runnable example for that model.

If you have questions, please feel free to reach out, and we will gladly get back to you!