Released v1.164.0 of doctl, the official DigitalOcean CLI.

The following Reflection AI model is now available on DigitalOcean Inference for serverless inference: Beam

The following Reflection AI model is now available on DigitalOcean Inference for serverless inference:

The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA Nemotron 3.5 Super VL

The following NVIDIA model is now available on DigitalOcean Inference for serverless inference:

In public preview, you can now create spend alerts for Serverless Inference model access keys.

Each key’s spend is tracked against its own monthly budget, and you receive email alerts as it crosses the thresholds you choose.

DigitalOcean Harness Runtime now supports OpenHands agents.

Run the OpenHands Agent Server in an isolated sandbox, create agents from OpenHands Agent Canvas or the DigitalOcean API, and connect a model such as one from DigitalOcean Serverless Inference. To set up an agent, see How to Run an OpenHands Agent on DigitalOcean Harness Runtime.

Inference Router has been redesigned as a single managed router.

Send requests to the inference-router model name, optionally with a routing_preference of balanced, budget, or quality, and the router selects the best model for each request.