Roleplay & chat frontends

Janitor AI

Roleplay site that connects through a reverse proxy.

Janitor AI uses a proxy slot for any OpenAI-compatible endpoint. Drop FreeTheAi in as a proxy and pick the model you want.

Base URLhttps://api.freetheai.xyz/v1

API path/chat/completions

Recommended modelsbbl/gpt-5.5-mini

Chat completions Streaming

Step by step

Connect Janitor AI to FreeTheAi.

5 steps

1
Open a chat
Pick a character on the home page and click `chat with` to land on the chat page.
2
Open API settings
Tap the three lines in the top right of the chat, then `API Settings`.
3
Switch to Proxy
In the API Settings panel, switch to the `Proxy` tab and click `+ New` to start a fresh config.

Use these exact values. Janitor AI requires the full URL with /chat/completions.

text

Name: freetheai
Model: bbl/gpt-5.5-mini
Proxy URL: https://api.freetheai.xyz/v1/chat/completions
API Key: PASTE_YOUR_FREETHEAI_KEY

5
Save
Click `Save`. Janitor AI will use FreeTheAi for new responses on this character.

Recommended aliases

See the full live catalog at /models. Aliases are stable; pricing on the free tier stays $0.

Heads up

Janitor AI sometimes shows a `Failed to fetch (unk)` error. That is usually Janitor-side instability, not FreeTheAi - try Chub or SillyTavern instead, or wait it out.
401 means the key is wrong. Use `/resetkey` in the FreeTheAi Discord and paste only the key value, no quotes or markdown.
Some models do not work for Janitor RP - try `bbl/gpt-5.5-mini` or `glm/glm-5.1` for the most reliable responses.

Where to next