Welcome to the V2 API Reference for our Hive models! This documentation provides guides on integrating with our V2 APIs and the response structures for every Hive model.

The V2 API is your primary endpoint for inference requests, offering two options to handle your needs:

/sync: For real-time inference. Check out Sync API Examples to learn more.
/async: For batch processing or tasks with flexible timing, using a callback. Explore Async API Examples to get started.

Getting Started

To begin using the V2 API, you’ll need an API key for authentication.

Visit our Authentication page for details on obtaining and using your keys securely.

Once you have your API key and endpoint, you can dive into our step-by-step guide on Creating Tasks in the API.

Why Choose Hive's APIs?

The V2 API is built to handle a wide variety of workloads, offering flexible support for both real-time and batched processing for large-scale tasks. It’s scalable, reliable, optimized for many use cases, and integrates well into existing workflows. The V2 API is an ideal solution for powering AI-based applications.