Connect Janitor AI to a DeepSeek proxy
Janitor AI lets you plug in your own OpenAI-compatible proxy under API Settings. This page gives the exact values for this gateway's DeepSeek model, taken live from this gateway's own /v1/models endpoint.
1. Open the proxy settings
- In a chat, click the gear icon in the top-right corner.
- Choose API Settings.
- Click Add Configuration.
2. Fill in the fields
| Field | Value |
|---|---|
| Config Name | anything you like, e.g. PrivateDeskAI |
| Model Name | deepseek-ai/DeepSeek-V4-Flash-0731 |
| Proxy URL | https://api.privatedeskai.com/v1/chat/completions |
| API Key | YOUR_SAGG_KEY (from the account page) |
Copy the Proxy URL exactly, including /chat/completions at the end - Janitor AI's own help article shows the full address for a proxy, not a shorter root address.
3. Save and test
- Click Add, then Save Settings.
- Refresh the page and start a chat to confirm it answers.
Model id and alias
The model id above, deepseek-ai/DeepSeek-V4-Flash-0731, and its short alias deepseek-v4-flash-fast, are both listed live at /v1/models - check that page if a name there ever differs from this one.
If something does not work
Re-check the Proxy URL character by character (a missing /chat/completions or an extra slash is the most common mistake) and that the API key was pasted without extra spaces. For what request parameters this API accepts, see Compatibility; for current uptime and speed, see Status.
Source for the Janitor AI steps above: Janitor AI's own help article, "TL;DR Quickstart Proxy Instructions" (help.janitorai.com), checked 2026-11-14. Janitor AI may change its own settings UI at any time.