AI Inference & Model Hosting
LLM inference APIs, GPU cloud, and model hosting platforms
OVHcloud AI
European sovereign AI infrastructure—GPU compute and managed LLM APIs from France
regolo.ai
EU-sovereign, zero-retention LLM inference on green Italian datacentres
Scaleway Generative APIs
EU-sovereign managed LLM inference from France's developer-first cloud provider
LightOn
Sovereign enterprise GenAI platform deployed on-prem, air-gapped, or EU cloud
Berget AI
Swedish sovereign AI inference platform with EU-only data residency
Nebius AI
European GPU cloud and LLM inference platform built for AI-native businesses
Prediction Guard
Privacy-first LLM API with built-in compliance and safety controls
Hugging Face Inference
World's largest open-model hub with managed inference endpoints for any model
Nscale
European AI hyperscaler with sovereign GPU cloud infrastructure in Norway and UK
OpenAI API
API platform for GPT, DALL-E, Whisper and other foundation models
Groq
Ultra-fast LPU inference for open-source LLMs at developer-friendly pricing
Fireworks AI
Fast, affordable open-source LLM inference API for production AI applications
Together AI
Open-source LLM inference and fine-tuning platform for enterprise AI builders
Modal
Serverless GPU compute platform for AI model training, inference, and data pipelines
Replicate
Run any machine learning model via API with a single line of code