LLMs & Privacy
When you use Kagi Assistant, we make API requests to third-party model providers to generate responses. We are committed to protecting your privacy and we don't set identifiers for any of our providers. 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 days¹ | |
|
| No | 30 days | |
|
| No | 30 days | |
|
| No | 30 days | |
|
| No | 24 hours | |
|
| No | 24 hours (Google Gemini API), up to 30 days (Google Vertex) | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| Not verified | Not verified | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | 30 days | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not stored | |
|
| No | Not specified⁴ |
¹ OpenAI is no longer required to retain all chat logs.
² o3/o3-pro models are not yet available to Kagi via Azure and go directly to OpenAI for now.
³ GPT 5 chat is labeled as ChatGPT in the Assistant.
⁴ Meta does not state a retention period for API requests.