DigitalOcean Serverless Inference: A Deep Dive
DigitalOcean introduced Serverless Inference, a fully managed API-first platform supporting 30+ foundation models across text, code, vision, image, video, and speech. It offers single-endpoint access,…
Digitalocean
252 mises à jour · 2026
70 feature updates·27 product launches·11 community·9 technical updates·7 content pieces·7 new integrations·6 pricing updates·5 partnerships
Parcourir d'autres années de Digitalocean
DigitalOcean introduced Serverless Inference, a fully managed API-first platform supporting 30+ foundation models across text, code, vision, image, video, and speech. It offers single-endpoint access,…
DigitalOcean unveiled a prefix-aware routing and caching mechanism to eliminate redundant LLM inference costs, targeting the 'prefill tax' where identical system prompts and shared contexts are recomp…
DigitalOcean launched its Inference Router in Public Preview, enabling dynamic model routing for AI coding agents like OpenCode to optimize cost, latency, and quality. The integration allows OpenCode …
Anthropic released Claude Opus 4.8, improving benchmarks and agentic task reliability while adding user-controlled effort levels, dynamic workflows for large-scale coding, and a 2.5× faster fast mode …
DigitalOcean introduced Batch Inference on its AI-Native Cloud, enabling high-volume asynchronous AI workloads at up to 50% lower cost than real-time inference. The feature supports OpenAI and Anthrop…
DigitalOcean’s AI-Native Cloud, powered by NVIDIA HGX B300 GPUs, enabled Hippocratic AI’s Polaris system to scale to 10 million patient calls with a 99.9% clinical safety score. The collaboration deli…
DigitalOcean launched generally available request-based autoscaling on App Platform, enabling apps to scale automatically based on live HTTP traffic signals like requests per second and P95 latency. P…
DigitalOcean introduced Inference Router, an infrastructure-level tool that automatically routes LLM requests to the best-fit model based on task requirements, optimizing for cost, latency, or quality…
DigitalOcean introduced a unified AI inference platform featuring serverless inference with 50+ models, dedicated GPU options, and an Intelligent Router that dynamically selects models based on cost, …
DigitalOcean now charges 18% VAT to Tanzanian customers and requires 15% withholding tax for certain digital service payments to non-residents, effective since July 2023. Tanzanian businesses must wit…
DigitalOcean added several new AI models to its Inference Engine, including Kimi K2.6, DeepSeek-V4-Pro, GPT-5.5, GPT Image 2.0, and Claude Opus 4.7. These models enable autonomous workflows, long-cont…
DigitalOcean unveiled the AI-Native Cloud, a five-layer platform purpose-built for AI inference and agentic workloads, shipping 15 new products at Deploy 2026. The stack spans silicon to agents, integ…
20 premières affichées. Cliquez un mois ci-dessus pour l'archive complète de Digitalocean.
Suivez Digitalocean en pilote automatique