Inference and AI infrastructure for developers and DevOps teams
Run your AI models and applications in a secure, EU-based environment with full control over your code and data.
Developer capabilities
GitOps-based infrastructure
Skip complex Terraform scripts and the AWS console. Define your infrastructure using simple YAML files in your Git repo.
Automatic sync – changes in your repo are automatically applied to your infrastructure
Version control – full history and ability to roll back changes
Portability – your infrastructure is defined as code and can be moved between environments
CI/CD integration – connect with your existing CI/CD pipelines
OpenAI-compatible API
Use the same code and libraries you're already using with OpenAI, but with full control over your data.
Minimal code change – just switch your API key and endpoint to migrate from OpenAI
Support for popular libraries – works with LangChain, LlamaIndex and other frameworks
GDPR-compliant – all data stays within the EU and is never stored
CO₂ tracking – get carbon emission data for every API call
Kubernetes without the complexity
Get the benefits of Kubernetes without having to manage the infrastructure yourself.
Preconfigured clusters – get started in minutes instead of days
Standardised Helm charts – install databases, caching and services with a single command
GPU support – run your own models on dedicated GPUs when needed
Autoscaling – automatically scale up and down based on demand
Developer tools that simplify
Tools to help you build, test, and deploy your AI applications faster.
CLI tools – manage your resources directly from the terminal
Logging and monitoring – built-in integration with Prometheus and Grafana
Cost tracking – see exactly what costs and optimise your resources
Developer environments – preconfigured environments for rapid development
Ready to start building?
Get started in under 5 minutes with our CLI tool and build your first AI application.
Models
View allAccess a broad selection of powerful open models to build diverse AI solutions.
Comprehensive model selection
- Broad selection of model types including instruct, re-rerank, and moderation models
- Optimised for agentic applications and complex AI workflows
- Support for multiple modalities: text, image, speech-to-text, and text-to-speech