Inference

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.

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.

The following Anthropic model is now available on DigitalOcean Inference for serverless inference: Claude Haiku 5.5

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

Prompt caching for DigitalOcean-hosted models is now in general availability.

All DigitalOcean-hosted models cache context automatically, with no code changes and no cache-write charge. Cache affinity routes requests with matching prefixes to the replica that holds the cache.

DigitalOcean Signals is now available in public preview for Harness Runtime agents and Serverless Inference.

Signals detects behavioral signals in conversations, such as a user asking for a human, a failed tool call, or an execution loop, so you can find the conversations that went wrong without reading every transcript. Signals collects data only after you opt in.

The Cost Analysis tab of the Billing page now includes Serverless Inference Live Usage, which lists the estimated cost and token counts of your Serverless…

The Cost Analysis tab of the Billing page now includes Serverless Inference Live Usage, which lists the estimated cost and token counts of your Serverless Inference requests by model and model access key, for both teams and organizations.

The Agent Development Kit (ADK), including the gradient-adk Python package and the gradient CLI, is deprecated.

You cannot deploy any new agents with ADK. Agents already deployed with ADK continue to run normally and you are billed for model usage. If you are using a DigitalOcean-hosted model, you are charged for those model keys.

You can now prepay for Serverless Inference and Managed Agents with the Inference and Agents balance, which no other products draw from.

Add $5 to $500 at a time or turn on auto-reload from the Billing page. Funds do not expire. You can also pay for eligible usage at a discount with a monthly plan, now in public preview. See Inference and Agents Balance and How to Pay for Harness Runtime.

The following OpenAI model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit: GPT-6.1 Sol

The following OpenAI model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit:

Released v1.175.0 of doctl, the official DigitalOcean CLI.

This release deprecates the doctl gradient commands.

The following Anthropic model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit: Claude Sonnet 5.5

The following Anthropic model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit:

The following NVIDIA model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit: Nemotron 3 Diarization

The following NVIDIA model is now available on DigitalOcean Inference for serverless inference and Agent Development Kit:

The following TypeSafe AI model is now available on DigitalOcean Inference for inference: Jev

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

The following Anthropic model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: Claude Opus 5.5

The following Anthropic model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents:

The following OpenAI models are now available on DigitalOcean Inference for serverless inference: GPT-6 Sol, GPT-6 Luna

The following OpenAI models are now available on DigitalOcean Inference for serverless inference:

The following DeepSeek model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: DeepSeek V4.1 Flash

The following DeepSeek model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents:

The following models are deprecated from DigitalOcean Inference as of 8 September 2026: Kimi K2.5, GLM 5, GLM-5.1, Nemotron-3-Super-120B (Public Preview)

The following models are deprecated from DigitalOcean Inference as of 8 September 2026:

The following OpenAI model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: GPT-6 Astra

The following OpenAI model is now available on DigitalOcean Inference for serverless inference, Agent Development Kit, and agents: