> For the complete documentation index, see [llms.txt](https://docs.meganova.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.meganova.ai/integration-guides/janitor-ai.md).

# Janitor AI

## Overview

Janitor AI is a popular AI character chat platform that allows users to interact with AI characters. This guide shows you how to integrate MegaNova's API as a backend for Janitor AI using OpenAI-compatible endpoints.

## Key Features

* Free tier available for supported models
* OpenAI-compatible API endpoints
* Multiple model options including Manta, DeepSeek, Meta LLaMA, Mistral, and Stheno
* No additional API key setup required beyond MegaNova credentials

## Requirements

* MegaNova account with API access
* [Janitor AI account](https://janitorai.com/) - Sign up for free
* API key from MegaNova

> **Usage Policy:** All integrations must comply with our [Terms of Service](/legal-docs/terms-of-service.md) and [Privacy Policy](/legal-docs/privacy-policy.md), including acceptable use policies and content guidelines.

## Integration Steps

### 1. Get Your API Key

![MegaNova API Keys Dashboard](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-7b3a3b1ef38fe479879d3e4c4e23d9610b516720%2Fapikey.png?alt=media)

1. Log into your [MegaNova AI](https://console.meganova.ai/home) and navigate to **API Keys** Page
2. Copy your default API key and securely store it

### 2. Open Janitor AI and Pick Your Character

1. Go to [Janitor AI](https://janitorai.com/)
2. You have two options:
   * **Create your own character**: Click "Create Character" to design a custom AI character with unique personality and traits
   * **Use existing characters**: Browse and select from thousands of available characters, such as **Fia** or any other character

![Create character](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-ebf8c239d4094fe16a7df9336f0eddf2a40359ab%2Fcreate_character_janitorai.png?alt=media)

Let's start a new chat with Fia

![Fia Character from Janitor AI](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-84e10b46c7467ee2fe769dd46bd3da61a069c244%2FFia.png?alt=media)

### 3. Configure MegaNova API

1. In the chat box, go to **using proxy**

![using-proxy](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-9c72f53b2d18a8c1176d94a2f502936f64378253%2Fusing_proxy_janitorai.png?alt=media)

2. Choose **Proxy**

![choose proxy](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-027e00cf33e7bc6e7033bb5346f16c3599772ca6%2Fchoose_proxy_janitorai.png?alt=media)

3. Enter the following configuration:
   * **Configuration Name**: anything you want
   * **API Endpoint**: `https://api.meganova.ai/v1/chat/completions`
   * **API Key**: Paste your API Key from step 1
   * **Model**: Choose from available ones like `manta-mini-1.0`, `manta-flash-1.0`, `manta-pro-1.0`, or other models

![api-setting](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-a8d3344ab98546b7bee002bbc3e0cec31ee25f97%2Fapi_settings_janitorai.png?alt=media)

### 4. Start Chatting!

That's it. You can now interact with your characters through the MegaNova-powered backend.

![chat with character](https://3323000882-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FidCsqEyuyxKpz0abGCcS%2Fuploads%2Fgit-blob-85b8095404553c813d7ab77a1443141be5ead8a1%2Fchat_janitorai.png?alt=media)

## Available Models

The following models are compatible with Janitor AI:

### Free Models (No Payment Required)

| Model                 | Description                                 | Best For                              | Pricing  |
| --------------------- | ------------------------------------------- | ------------------------------------- | -------- |
| `manta-mini-1.0`      | Lightweight dialogue-optimized model        | Quick responses, casual chat          | **Free** |
| `L3.3-MS-Nevoria-70B` | 70B parameter model for advanced reasoning  | Long-form dialogue, complex reasoning | **Free** |
| `L3-70B-Euryale-v2.1` | 70B parameter creative writing model        | Creative writing, storytelling        | **Free** |
| `L3-8B-Stheno-v3.2`   | 8B parameter efficient model                | General tasks, efficient generation   | **Free** |
| `DeepSeek-V3-0324`    | 685B parameter model for advanced reasoning | Advanced reasoning, complex tasks     | **Free** |

> **Free Model Usage:** Free models have daily limits and are intended for evaluation and interactive use only, not production workloads.

### Paid Models

| Model             | Description                             | Best For                                    | Pricing                   |
| ----------------- | --------------------------------------- | ------------------------------------------- | ------------------------- |
| `manta-flash-1.0` | Balanced tier for general-purpose use   | General conversations, balanced performance | $0.02/1M in, $0.16/1M out |
| `manta-pro-1.0`   | Advanced tier with long context support | Complex dialogue, detailed interactions     | $0.06/1M in, $0.50/1M out |
| `llama-3.1-405b`  | Meta's large model                      | Detailed character interactions             | Paid                      |
| `mistral-24b`     | Balanced performance                    | Natural conversation flow                   | Paid                      |
| `stheno-v3.2`     | Creative writing model                  | Roleplay, assistant-style dialogue          | Paid                      |
| `gemini-2.5`      | Google's advanced model                 | Multimodal interactions, high quality       | Paid                      |

## Character Configuration

When creating or editing characters in Janitor AI:

1. Set **API Type** to "OpenAI Compatible"
2. Configure **Temperature** (0.7-0.9 recommended for roleplay)
3. Set **Max Tokens** (2048-4096 recommended)
4. Add character-specific prompts in the **System Message**

## Advanced Configuration

#### Custom System Prompts

```
You are [Character Name], a [character description]. 
You are engaging in a roleplay conversation. 
Stay in character and respond naturally to the user's messages.
```

#### Temperature Settings

* **0.7-0.8**: Balanced creativity and consistency
* **0.8-0.9**: More creative and varied responses
* **0.9-1.0**: Maximum creativity (may be less coherent)

## Troubleshooting

### Common Issues

#### API requests failing

* Verify your API key and endpoint URL
* Ensure you have sufficient credits in your MegaNova account

#### Responses are too short/long

* Adjust the "Max Tokens" setting in Janitor AI
* Recommended: Start with 2048 tokens and adjust based on needs

#### Network error or bot refuses to generate reply

This is normal when using proxy configurations.

**Quick Fix**:

1. Save your proxy configuration
2. Refresh (reload) the Janitor AI page
3. Reopen your chat and continue

Your settings will be preserved after refresh.

### Rate Limits

MegaNova API has rate limits based on your tier:

* **Free Tier**: 10 requests per minute
* **Paid Tiers**: Higher limits, see [Tier Overview](/tiers.md)

## Support

* **MegaNova Support**: [Contact Us](/resources/contact-us.md)
* **Janitor AI Community**: [Official Discord](https://discord.gg/janitorai)
* **API Documentation**: [MegaNova API Reference](/api-reference.md)

## Conclusion

This integration allows you to use MegaNova's API models with Janitor AI through OpenAI-compatible endpoints. For additional support or questions, refer to the resources listed in the Support section above.