Deploy a Rapid Model

Deploy a Rapid model as a serverless Workflow API with code snippets, and customize the underlying Workflow.

When you create a Rapid model, a Workflow will be automatically created to run your model. This Workflow will be powered by the Serverless Cloud API.

Rapid will show code snippets in various programming languages that you can use to integrate your model into your applications:

Confidence Threshold

If your Workflow supports a confidence input, a confidence threshold slider will appear in the deploy sidebar. Use it to filter out low-confidence predictions before integrating the API into your application. The deploy preview will update in real time so you can see the effect of your chosen threshold.

Customize Your Workflow

You can customize your API to add new features by clicking the "Open Roboflow Workflows" link in the bottom right corner. This will open the Roboflow Workflow that powers your cloud API. You can customize your Workflow in whatever way you want. For example, you could add a ByteTrack block to add stateful object tracking capabilities to your API.