Lyceum

Lyceum

Serverless and dedicated open model hosting in Europe, pay as you scale.

Visit Lyceum

About Lyceum

Lyceum is an AI infrastructure platform designed for teams and businesses who need to run, scale, and serve open AI models reliably out of European data centers. Users can access serverless inference on pay-per-token pricing, reserve GPUs for dedicated endpoints, or rent GPU compute by the second for custom model training and inference. The service emphasizes data security, with zero data retention and no use of user prompts for training, and provides OpenAI-compatible APIs for drop-in integration. Support is offered directly from engineers, with Slack channels available to business customers.

Pricing Plans
Serverless
From $0.06/mo
On-Demand VMs
From $1.19/mo
Long-term Contracts
Contact us

Resources

Product Website

Visit Lyceum's official website for product details and getting started.

Visit website →

Documentation

Comprehensive API reference and integration guides for using Lyceum's GPU compute services.

View docs →

Blog

Insights and updates on AI development, use cases, and best practices with Lyceum.

Read blog →

Pricing

Detailed pricing structure for Lyceum's GPU compute services and plans.

See pricing →

Documentation

Comprehensive API reference and integration guides for using Lyceum's platform.

View docs →

Blog

Insights and updates on AI infrastructure trends and best practices.

Read blog →

Pricing

Details on pay-per-token pricing, GPU reservations, and compute rental options.

See pricing →