Products
Models API
Call 30+ open-source models through one OpenAI-compatible API. Pay per token.
Serverless GPU
Deploy any model on the GPU you choose. Billed per second, scale to zero.
Cloud GPU
On-demand NVIDIA GPU instances with SSH access, hosted in Europe.
GPU Clusters
Reserved multi-node GPU clusters for large-scale training and inference.
Models API or Serverless GPU?
Ready-made models billed per token, or your own model billed per second. See which one fits.
Compare the two →
Use cases
Inference
Serve models in production, from API calls to dedicated endpoints.
Coding
Use open-source coding models in your IDE with our VS Code extension.
Agentic AI
Power agents and tool-calling workflows with sovereign inference.
Training
Train models from scratch on multi-GPU instances and clusters.
Fine-tuning
Adapt open-source models to your data and your domain.
Your data stays in France
Our own NVIDIA GPU servers in Paris and Lyon. Your prompts and outputs are never used to train models.
About Arkane Cloud →
