SLA - On-Demand Inference
No SLA During Private Preview
On-Demand Inference is currently in private preview. No Service Level Agreement (SLA), availability target, uptime commitment, or service-credit scheme applies to the service during the private preview.
Service Commitments
The private preview has no guaranteed endpoint availability, inference latency, throughput, model performance, or model availability. The service, its models, and its capabilities can be changed, interrupted, or retired during the preview.
On-Demand Inference is intended for evaluation during the private preview and should not be used for workloads that require a contractual production service level.
Client Responsibilities
Clients remain responsible for:
- securing AI API keys and controlling access to the endpoint;
- validating model outputs, behavior, and suitability for their use case;
- managing prompts, inputs, outputs, and their legal or regulatory compliance;
- monitoring usage and costs; and
- designing applications to handle request failures, interruptions, model changes, and changes to preview limits.
For the complete shared-responsibility framework, see the Exoscale Shared Responsibility Model.
After the Private Preview
If Exoscale introduces an SLA for On-Demand Inference after the private preview, the applicable availability target, exclusions, service credits, and effective date will be documented on this page.