New

Sandboxes, in private preview: isolated microVMs for AI agents, compatible with the E2B SDKs.Read more

Serenity Edge

Infrastructure

Our own inference nodes in Spain

No third-party clouds for inference: our own infrastructure, in Spain, operated by a Spanish company.

Every request enters through the Serenity Edge API, is served on one of our inference nodes and returns to your application. One base URL gives access to the whole catalogue, so you never need to know which node served your request.

  1. Your application
  2. api.serenityedge.ai
  3. Our own nodes in Spain
  4. Response
The path of a requestEuropean UnionResponseYour applicationapi.serenityedge.aiOur own nodes in Spain

Our own infrastructure

We operate the nodes that serve the models directly. That lets us control where data is processed and how each model is served.

How your data is handled

A replicable network of nodes

Models are served from replicable nodes in Spain, added as demand grows.

The path of a request, in the documentation

A single API

A single OpenAI-compatible API at api.serenityedge.ai gives access to the whole catalogue, at the same prices whichever node serves the request.

The API reference

The Serenity family

Serenity Edge is the inference infrastructure behind the Serenity Star agent platform. The same infrastructure that serves the platform is now available through the API.

Access with a Serenity Star account

Service status is published at status.serenityedge.ai.Service status

Try it with your own code

Change the base URL and make your first request.