# Use Outrun with Janitor AI: Proxy URL and Model ID

> Connect Janitor AI to Outrun with the full chat completions Proxy URL, your API key and a model ID. For adults 18+. Includes common errors and FAQ.

Canonical: https://outrun.to/docs/setup/janitor-ai

Connect Janitor AI to Outrun in your browser with your key and a model.

**For adults.** You must be 18 or older to use Janitor AI with Outrun.

## Before you start

Have your API key and some Outrun credit ready. Keep your key private.

[Get your API key](https://outrun.to/api-keys)

[Check balance](https://outrun.to/balance)

[Choose a model](https://outrun.to/docs/models)

**Optional setup helper Use an AI assistant to walk through these steps**

Copy the setup instructions into an AI assistant you already use. Review any file changes it suggests before allowing them.

Enter your API key directly in the app or local settings. Keep it out of the assistant’s chat.

**Connection settings Show ⌄**

Connection settings

```
Config Name: Outrun
Proxy URL: https://api.outrun.to/v1/chat/completions
Model Name: claude-sonnet-5-5
```

Get your key from Outrun → API keys and enter it privately in the app or local settings. Test with “Reply with OK only.” Tests use credit; check Activity before retrying.

## Setup Steps

1. 1

  **Get your Outrun key**

  Open API keys on the Outrun website, or open @outrunAPI_Bot and choose My API key. Paste your key only into Janitor AI's API Key field.

2. 2

  **Open API Settings**

  Log in to Janitor AI and open a chat. At the top right, click the gear icon, choose API Settings, then Add Configuration.

3. 3

  **Choose the proxy option**

  If Janitor AI asks which API source to use, choose its proxy (custom) option instead of a built-in model.

4. 4

  **Fill in each field**

  Config Name: any name you like, such as Outrun. Model Name: the exact model ID, for example claude-sonnet-5-5. Proxy URL: https://api.outrun.to/v1/chat/completions (Janitor AI needs the full chat completions URL, not only /v1). API Key: paste your own Outrun key. Leave Custom Prompt blank for now.

5. 5

  **Save and refresh**

  Click Add, then Save Settings, and refresh the whole page. Open the configuration and make sure it shows as Active.

6. 6

  **Send one short test**

  Open a chat and send a short message such as: Reply with OK only. This uses Outrun credit. If a reply is empty or interrupted, check Activity before trying another model.

## General chat models

Choose a model you already use. Open its detail page for current prices, limits and route options.

| Model | Model ID | Details |
| --- | --- | --- |
| Claude Sonnet 5.5 | claude-sonnet-5-5 | Model details |
| DeepSeek V4 Pro | deepseek-v4-pro | Model details |
| GPT-6.1 Sol | gpt-6.1-sol | Model details |

## Roleplay and fiction-writing models

These uncensored and abliterated text models are live. They suit long character roleplay and fiction writing. Open a model page to compare routes, limits and current prices.

| Model | Model ID | Details |
| --- | --- | --- |
| glm-5.3-abliterated | glm-5.3-abliterated | Model details |
| DeepSeek V4.1 Flash Abliterated | deepseek-v4.1-flash-abliterated | Model details |

## Context, response length and streaming

Janitor AI sends the character, memory and chat history with every message. Keep the chat within the model's context limit; long chats cost more credit per message because the whole history is sent again.

If Janitor AI lets you cap response length, keep it within the Response limit below. If replies appear all at once, check Janitor AI's Text Streaming setting. Larger prompts can fall into another pricing tier; check the linked model page.

| Model ID | Context limit | Response limit | Streaming |
| --- | --- | --- | --- |
| claude-sonnet-5-5 | 1,000,000 tokens | 128,000 tokens | On |
| deepseek-v4-pro | 1,000,000 tokens | 393,216 tokens | On |
| gpt-6.1-sol | 1,050,000 tokens | 128,000 tokens | On |
| glm-5.3-abliterated | 1,000,000 tokens | 130,000 tokens | On |
| deepseek-v4.1-flash-abliterated | 1,000,000 tokens | 65,536 tokens | On |

## Test your key first

This optional cURL request separates a key or balance problem from an app setting. Put your key in OUTRUN_API_KEY privately before running it. One model request uses credit; check Activity before retrying.

Chat Completions test

```
curl https://api.outrun.to/v1/chat/completions \
  -H "Authorization: Bearer $OUTRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-sonnet-5-5","messages":[{"role":"user","content":"Reply with OK only."}],"max_tokens":16}'
```

## More models

Janitor AI works with any Outrun text chat model. Copy the exact model ID into Model Name.

[Browse model pages](https://outrun.to/model/)[API formats and endpoints](https://outrun.to/docs/api)

## Common errors

**401: key missing or rejected**

Copy your current key from API keys and paste it into Janitor AI's API Key field with no spaces. Save, then try again.

**402: not enough available credit**

Check Balance and the key's spending cap. Another request may have temporarily reserved credit; read the message before adding funds.

**404: model or URL not found**

Copy the model ID exactly into Model Name. A general network error usually means the Proxy URL is wrong or the page was not refreshed after saving. It must be exactly https://api.outrun.to/v1/chat/completions with no extra slashes.

**429: busy or rate limited**

Wait for the active request to finish or the rate limit to reset, then try again. Do not resubmit the same request repeatedly.

**Model choices and service notes**

Use a currently available text chat model from Models & Pricing; paused models cannot be used. Tests and chats use prepaid Outrun credit. Check Activity before repeating an interrupted request.

[Contact @outrunsupport](https://t.me/outrunsupport)

## Frequently asked questions

**What Proxy URL do I use for Janitor AI?**

Use https://api.outrun.to/v1/chat/completions. Janitor AI needs the full chat completions URL, not only the /v1 base.

**Which model name should I enter?**

Enter an exact model ID from Models & Pricing, such as claude-sonnet-5-5. A display name or a typo returns a 404 error.

**Do I need to refresh after saving?**

Yes. Click Save Settings, refresh the whole Janitor AI page, then check that your configuration shows as Active.

**Is this for adults only?**

Yes. Janitor AI is for adults aged 18 and over. Only connect it to Outrun if you are 18 or older.

**Does Outrun store my chats?**

Outrun does not store your prompts, images or outputs unless you choose to save them. Janitor AI keeps your chat history in your Janitor AI account.

**Which models suit long roleplay?**

The uncensored and abliterated text models listed above suit long character roleplay and fiction writing. Check the context limit and the model page before you pick one.