---
title: "JanitorAI API: FreeTheAI Proxy Setup"
description: "Use models like GLM 5.3, Kimi K3, and MiniMax M3 on JanitorAI. The exact proxy URL, API key, and model name for FreeTheAI, plus fixes for common errors."
url: https://freetheai.org/setup/janitor-ai
language: en
updated: 2026-09-29
---

# JanitorAI API: FreeTheAI Proxy Setup

JanitorAI connects to FreeTheAI through its Proxy settings. You paste the full chat completions URL, your key, and a model ID, then refresh the page.

## Settings

- Configuration Name: `FreeTheAI`
- Model Name: `glm-5.3`
- Proxy URL: `https://api.freetheai.org/v1/chat/completions`
- API Key: `your FreeTheAI key (ftai_..., 53 characters)`

## Steps

1. **Open a chat.** Open any character and start a chat. The character must allow proxies.
2. **Open API Settings.** Tap the menu (three lines) at the top right of the chat, then API Settings.
3. **Add a proxy configuration.** Choose Proxy, then + Add Configuration, and fill in the values from the table above. The Proxy URL must end in /chat/completions. Leave Custom Prompt empty for now.
4. **Save and refresh.** Press Save Settings, then refresh the page (Ctrl+Shift+R on a computer). JanitorAI only loads a new proxy after a full reload.
5. **Add funds and chat.** Paid models bill your wallet. Add funds at freetheai.org/dashboard/wallet and follow a provider of the model on its page, then send a message.

## Tips

- Setting Max new tokens to 0 asks for the model's full output limit.
- Keep streaming on for long replies.
- Copy model IDs exactly as freetheai.org/models lists them.

## Troubleshooting

**Why does JanitorAI say "network error" or "Failed to fetch"?**

The Proxy URL is wrong or the page was not refreshed after saving. Use https://api.freetheai.org/v1/chat/completions exactly, save, and reload the page.

**Why do I get a 401 error?**

The key is wrong or incomplete. Paste the whole ftai_ key (53 characters). The short ftai_1234567... shown in your key list is only a prefix.

**Which model is best for JanitorAI roleplay?**

Start with glm-5.3. kimi-k3.1-pro and minimax-m3 are good alternatives. The full list with prices is at freetheai.org/models.

**It still says "Failed to fetch" with the right URL. What else can I try?**

That error often comes from JanitorAI itself, mostly in the app. Use janitorai.com in a browser instead, and try turning off prefill and text streaming.

**Why do I get a 403 error?**

A 403 usually means the account follows no provider of that model, or your email is not confirmed. Follow a provider on freetheai.org/providers, then try again.

**Why do I get a 429 error?**

Your previous reply is still being written. Wait for it to finish, then send again.

**The model is busy or the reply is empty. What should I do?**

Reroll the message, or switch to another model. freetheai.org/status shows which models are up.

**Why are replies cut off?**

Raise Max new tokens in Generation Settings, or set it to 0 to ask for the model's full output.

**Can I turn thinking off on JanitorAI?**

JanitorAI has no thinking setting, but you can turn thinking off for your key: on freetheai.org/dashboard/api-keys, edit the key and switch on Turn thinking off.

**How do I get longer or shorter replies?**

Ask for it in your prompt, for example "Response length: about 300 words", and set Max new tokens high enough.

**Does FreeTheAI work through Lorebary?**

No. Connect JanitorAI to FreeTheAI directly with the Proxy URL above.

Checked: Checked against JanitorAI's help center proxy guide and current setup guides on 2026-09-29.