Inference PyDo SDK Reference
Last verified 30 Sep 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.
PyDo is the official DigitalOcean Python client library. Install it with pip install pydo.
The Inference modules are:
-
Dedicated Inference: Manage dedicated inference endpoints, including their accelerators, CA certificate, sizes, GPU model configuration, and access tokens. Dedicated Inference is available in public preview. You can opt in from the Feature Preview page.
-
Serverless Inference: Access and use serverless inference models.
-
Agent Platform: Build agents with pre-built or custom foundation models, add function and agent routes, and create retrieval pipelines backed by knowledge bases.
-
Agent Inference: Integrate agents into your applications using an agent-specific endpoint.
For install instructions, quickstart examples, and the SDKs available for other languages, see SDK and Client Libraries.