Janitor AI
Janitor AI-style clients can change their proxy settings over time, so use this page as a neutral checklist rather than a UI-by-UI guide. rout.my works anywhere the client lets you enter an OpenAI-compatible proxy URL, key, and model name.
For the current proxy-style setup, paste the full chat completions URL:
text
https://api.rout.my/v1/chat/completionsValues
| Field | Value |
|---|---|
| Proxy URL / Other API URL | https://api.rout.my/v1/chat/completions |
| API Key | Your rout.my key |
| Model Name | Exact model ID from /v1/models |
| Base URL fallback, only if a client appends the route for you | https://api.rout.my/v1 |
If the client has an option like "append /chat/completions", enable it only when you entered the base URL. Keep it disabled when you entered the full proxy URL above.
Test outside Janitor
bash
curl https://api.rout.my/v1/chat/completions \
-H "Authorization: Bearer $ROUTMY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "provider/model-id",
"messages": [{ "role": "user", "content": "Hello" }]
}'Common issues
| Problem | Fix |
|---|---|
| 404 | The proxy URL is usually missing /v1/chat/completions, or /chat/completions was appended twice. |
| 401 | Create a fresh key and paste it without spaces. |
| Model not found | Copy the model ID exactly from /v1/models. |
| Saved but no replies | Hard refresh Janitor after saving the proxy config. |