Qwen3.8-Max, a 2.4 trillion-parameter mixture-of-experts model, is now available on DigitalOcean Inference Engine through Serverless Inference. This is an updated release in the Qwen3.8 family: on top of the long-context and agentic strengths of the earlier Qwen3.8 model, Qwen3.8-Max adds native image and video input, and a 1M-token context window built in.

DeepSeek-V4-Pro-0813 is a 1.6T-parameter, 49B-active MoE reasoning model now available through DigitalOcean Serverless Inference and Inference Router. It scores 53 on the Artificial Analysis Intelligence Index, well above the open-weights median of 27, and supports a 1M-token context window under an MIT license with no commercial-use restrictions.

Alibaba's Qwen3.8-2.4T-A95B, a 2.4T-parameter MoE model with a 1M-token context window is now available via DigitalOcean Serverless Inference.

Spot GPU Droplets are now in Public Preview, giving you access to latest-generation GPUs for short-lived, fault-tolerant work like batch training, batch inference, and rendering.

Droplets are interruptible and can be reclaimed at any time. We aim to give at least two hours' notice. Terms and Conditions apply.

Provision today

DeepSeek-V4-Flash-0731, DeepSeek's latest release optimized for agentic coding and autonomous workflows, is now available through DigitalOcean Inference Engine. A 284B-parameter mixture-of-experts model with only 13B parameters active per request, this model delivers fast inference at a fraction of the compute cost of a dense model of comparable size. A full re-post-training pass focused on autonomous task execution pushes its agentic performance ahead of DeepSeek's own V4-Pro, despite the smaller active parameter count. It excels at repo-scale coding agent workflows, multi-step tool use, and production-grade agentic loops.

Access the model now ->

Kansas City (MKC1) is now available as our newest DigitalOcean data center region. MKC1 expands DigitalOcean's footprint to 20 data centers across 11 global regions. MKC1 is a fully liquid-cooled data center and runs NVIDIA B300 GPUs.

Available at launch:

MKC1 has achieved an ISO 27001:2022 certification alongside SOC 2 Type II, which is reflected in a SOC 3 Type II report. These certifications can be accessed in our Security Reports and Certifications Center. As with every DigitalOcean region, you get the full platform in one place and on one bill, so your inference, compute, storage, databases, and apps sit together instead of across vendor boundaries.

Kimi K3 is the first open 3T-class model, with a 1M-token context window that ingests entire codebases and long documents without chunking. Its sparse expert architecture (2.8T parameters, 16 of 896 active per token) delivers frontier-scale capability with efficient inference, and native multimodal support lets it reason over text, images, and video together. Tuned for max thinking effort by default, it sustains long-horizon autonomous work like coding, research automation, and multi-hour agentic sessions.

Claude Opus 5, Anthropic's latest flagship model for coding, reasoning, and knowledge work, is now available through DigitalOcean Inference Engine. Designed for demanding agentic workflows, Opus 5 delivers frontier-level performance with improved cost efficiency, offering intelligence close to Claude Fable 5 at half the price. It excels at complex software engineering, scientific research, and business automation tasks, while supporting long-context reasoning, tool use, and structured outputs.

Model synthesis is a new opt-in server-side tool in DigitalOcean Inference Engine. Run multiple models on the same inference request and get a single synthesized response, no custom orchestration required. Built for complex, high-reasoning tasks, it works with the existing Chat Completions, Responses, and Messages APIs. Choose an optimized preset or configure the panel and synthesizer directly.

OpenAI's GPT-5.6 family, Sol (flagship), Terra (balanced), and Luna (fast, cost-efficient), is now available through DigitalOcean Serverless Inference. Sol delivers state-of-the-art performance across coding, knowledge work, cybersecurity, and scientific reasoning, while Terra provides a balanced option for everyday production workloads and Luna offers their fastest, most affordable model in the family. New reasoning and mode help tackle complex, multi-step tasks.