Nscale Serverless Inference

Dedicated AI infrastructure stack combining GPU-on-Demand compute, Object Storage, and managed model hosting for end-to-end AI workloads on Italian-sovereign infrastructure

Build generative AI applications with foundation models from Anthropic (Claude Opus 4.7 from April 2026), Cohere, Meta, Mistral, Stability AI, TwelveLabs (video understanding), and Amazon's own Nova family — accessed via a single API with fine-tuning, knowledge bases, agents, and a model marketplace for discovery and easy onboarding

Enterprise access to OpenAI models including GPT-4, GPT-3.5, and DALL-E with Azure security, private networking, regional deployments, and pay-as-you-go or provisioned throughput

Dedicated AI/ML infrastructure combining GPU compute, Object Storage for datasets, and managed model hosting on Swiss-resident infrastructure — positioned for regulated EU customers needing AI workloads outside US jurisdiction

Unified platform to build, deploy, and scale ML models with AutoML, custom training on TPUs and GPUs, model registry, pipelines, feature store, and generative AI studio

Sovereign Swiss AI suite: managed inference endpoints for open-source LLMs (Llama, Mistral), AI Studio chat interface (Kchat), and document-analysis APIs — positioned as the Swiss-resident alternative to hosted OpenAI / Anthropic APIs

Managed hosting and inference endpoints for open-source large language models (Llama, Mistral, DeepSeek) running on EU-resident GPU infrastructure with OpenAI-compatible API, positioned as the GDPR-resident alternative to OpenAI / Anthropic hosted APIs

Managed inference service hosting Cohere Command and Embed plus Meta Llama large language models — pay-per-token chat / completion / embedding APIs, plus fine-tuning on customer datasets via dedicated AI clusters

Managed AI platform hosting Mistral AI models (including Le Chat Enterprise) on Outscale's SecNumCloud-eligible French infrastructure — positioned as the strictest-sovereignty alternative to hosted OpenAI / Anthropic / Bedrock APIs for European public-sector and regulated workloads

Managed serverless inference endpoints for open-source large language models (Llama, Mistral, DeepSeek), with OpenAI-compatible API and per-million-tokens pricing — positioned as the EU-resident alternative to hosted OpenAI / Anthropic APIs

Managed serverless inference endpoints for hosted open-source LLMs (Llama, Mistral, DeepSeek) with OpenAI-compatible API and per-million-tokens pricing — distinct from Scaleway's full AI Platform (training + custom-model hosting)

Managed serverless inference endpoints for hosted open-source LLMs (Llama, Mistral) with OpenAI-compatible API and per-million-tokens pricing — positioned as the German-sovereign alternative to hosted OpenAI / Anthropic APIs