LLMs & Privacy
When you use The Assistant, we make API requests to third-party model providers to generate responses. We are committed to protecting your privacy. The table below provides an overview of how each provider handles your data, including training practices, retention policies, and links to their privacy documentation.
| Model | Model Provider | Trains on User Data via API | Data Retention for API | Privacy Policy / FAQ |
|---|---|---|---|---|
|
| No | 30 days (flagged prompts: 2 years) | |
|
| No | 30 days² | |
|
| No | 30 days | |
|
| No | 30 days | |
|
| No | 30 days |
|
| No | 24 hours | ||
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored |
|
|
| No | Not stored |
|
|
| No | Not stored | |
|
| No | 30 days | |
|
| No | Not stored |
¹ The Assistant does not include a unique user identifier for these requests.
² When our Azure OpenAI Service API quota is saturated, the request is sent to the fallback provider: OpenAI's own API. OpenAI is currently required by court order to retain all chat logs. We are working with Microsoft to raise the Azure quota and minimize these fallbacks.
³ o3/o3-pro models are not yet available to Kagi via Azure and go directly to OpenAI for now.