Privacy and Logging

When using AI through Siraya Model Router, whether via the chat interface or the API, your prompts and responses go through multiple touchpoints. You have control over how your data is handled at each step.

Within Siraya Model Router

Siraya Model Router does not store your prompts or responses.

Any categorization of your prompts is stored completely anonymously and never associated with your account or user ID.

Siraya Model Router does store metadata (e.g. number of prompt and completion tokens, latency, etc) for each request.

Provider Policies

Training on Prompts

Each provider on Siraya Model Router has its own data handling policies. We reflect those policies in structured data on each AI endpoint that we offer.

Wherever possible, Siraya Model Router works with providers to ensure that prompts will not be trained on, but there are exceptions. If you opt out of training in your account settings, Siraya Model Router will not route to providers that train. This setting has no bearing on Siraya Model Router's own policies and what we do with your prompts.

Data Retention & Logging

Providers also have their own data retention policies, often for compliance reasons. Siraya Model Router does not have routing rules that change based on data retention policies of providers, but the retention policies as reflected in each provider's terms are shown below. Any user of Siraya Model Router can ignore providers that don't meet their own data retention requirements.