This page covers AI Services. Compute, networking, and storage products have separate boundaries — contact helpdesk@nscale.com for product-specific guidance.
Legend
| Marker | Meaning |
|---|---|
| You configure, supply, or operate this control. | |
| Both parties contribute; obligations are split. | |
| Nscale implements, operates, and assures this control. | |
| Not applicable to this service. |
Your layer
Controls you configure, supply, or operate. Nscale has no visibility into the substance of these decisions and cannot assume responsibility for them.| Control | Serverless inference | Fine-tuning | Datasets |
|---|---|---|---|
| Prompt & query content | |||
| Training data content & quality | |||
| Service tokens & access control | |||
| Application & integration code | |||
| Input / output data retention & privacy | |||
| Regulatory & legal compliance | |||
| Model & inference parameters | |||
| Fine-tuning job configuration |
Boundary
Controls where obligations are split. Nscale provides the underlying capability; you are responsible for using it correctly within your application and operational processes.| Control | Serverless inference | Fine-tuning | Datasets |
|---|---|---|---|
| Encryption in transit (TLS) | |||
| Billing & usage monitoring | |||
| Incident response & notification |
Nscale layer
Controls Nscale implements, operates, and assures on your behalf as part of the managed service.| Control | Serverless inference | Fine-tuning | Datasets |
|---|---|---|---|
| Base model weights & updates | |||
| Inference serving runtime | |||
| Fine-tuning compute & runtime | |||
| Dataset storage & integrity | |||
| Autoscaling & availability SLA | |||
| GPU compute & virtualisation | |||
| Network security & DDoS protection | |||
| Physical infrastructure & data center |
Related
- Service Level Objectives — support hours, response targets, and incident priority definitions.
- Terms — contractual terms governing your use of Nscale services.