Inference provides a interface for managing inference workflows.
Inference Details
Generated on 28 Apr 2026
Inference provides a single control plane for managing inference workflows. It includes a Model Catalog where you can view available foundation models, including both DigitalOcean-hosted and third-party commercial models, compare model capabilities and pricing, use routing to match inference requests to the best-fit model, and run inference using serverless or dedicated deployments.
Inference itself has no cost. Pricing depends on the features you use within Inference, such as serverless inference or dedicated deployments, and the models and resources used for those requests.
Regional datacenter availability for Inference.
Limits and known issues for Inference.