Synchronous and Asynchronous Endpoint Inference

Web UI, REST API, and Python SDK are available for running inferences

You can either use pre-built OctoAI templates, cloned templates, or an endpoint created from your own models. To integrate OctoAI endpoints into your application, there are two main paths you can use:

  1. Our Python client, which supports both synchronous and asynchronous inferences for our "Quickstart" template endpoints. Read more about it here.
  2. Our HTTP REST API, which supports both synchronous and asynchronous calls for all endpoints. Read more about it here.