MODELS
Unlimited Basic subscription: unlimited Qwen 3.8 27B for €14.95/month, with no per-token billing

Documentation

Guides for deploying models, connecting the OpenAI-compatible API, and configuring routing, protection, and retrieval.

Deployment

Deployment lifecycle

Understand what QDivZero checks between launch and the first successful inference request.

Before capacity is requested

QDivZero validates the model source, runtime support, estimated memory, account policy and available balance. Smart selection also verifies that at least one provider satisfies the configured constraints.

Lifecycle states

A deployment moves through provisioning and starting before it becomes running. Stopping releases active compute while keeping the QDivZero configuration available for a later start.

  • Provisioning: capacity is being prepared.
  • Starting: the runtime and model are loading.
  • Running: the endpoint can receive requests.
  • Failed: inspect the recorded reason before retrying.

Recover safely

Retry transient provider failures. For memory errors, select more capacity or reduce runtime requirements. For billing blocks, restore the balance before starting again.