Releasesby IbisIn public preview, you can now create spend alerts for Serverless Inference model access keys
Preview11 days agoUnverifiedAdded Oct 20, 2026
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. You can also …
More DigitalOcean releases
Every DigitalOcean releaseSimulation is now available in public preview
Simulation is now available in public preview. Simulation tests agent behavior through generated, multi-turn conversations using scenario sets, user simulator models, judge models, and conversational metrics.
Inference Router has been redesigned as a single managed router
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. …
DigitalOcean Harness Runtime now supports OpenHands agents
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 …
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA...
The following NVIDIA model is now available on DigitalOcean Inference for serverless inference: NVIDIA Nemotron 3.5 Super VL For more information, see the Available Models page.
The following Anthropic model is now available on DigitalOcean Inference for serverless inference: Claude...
The following Anthropic model is now available on DigitalOcean Inference for serverless inference: Claude Haiku 5.5 For more information, see the Available Models page.
DigitalOcean MicroVMs are available in public preview in MKC1
DigitalOcean MicroVMs are available in public preview in MKC1. MicroVMs are lightweight virtual machines that run a container image in its own kernel, pause automatically when idle, and resume on the next request with memory, files, and …
Prompt caching for DigitalOcean-hosted models is now in general availability
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 …
Starting with DOKS 1.37, GPU device plugins are no longer enabled by default on clusters with GPU nodes
Starting with DOKS 1.37, GPU device plugins are no longer enabled by default on clusters with GPU nodes. Dynamic Resource Allocation (DRA) drivers are available as opt-in cluster plugins (nvidia_gpu_dra_driver or amd_gpu_dra_driver). Device …
Also shipped on Oct 13, 2026
DigitalOcean in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
The AI.AGG function is generally available (GA)
The AI.AGG function is generally available (GA). You can use this function to semantically aggregate unstructured input data based on natural language instructions.
BigQuery generative AI functions now support the gemini-4-argon model
BigQuery generative AI functions now support the gemini-4-argon model. This model is generally available .
Gemini 4 Argon in CodeMender (Preview)
CodeMender now supports Gemini 4 Argon. To use it, pass --model gemini-4-argon to cm find , cm verify , or cm fix . Gemini 3.8 Flash remains the default model. For more information, see Specifying the model .
Gemini 4 Argon and Gemini 4 Argon Cyber Permissive
Gemini 4 Argon ( gemini-4-argon ) is available in General Availability (GA) . Gemini 4 Argon is Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
On-demand state repartitioning is now generally available
On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .