Can Janitor AI use OpenRouter?

Yes. Janitor AI supports OpenRouter for accessing 300+ models through a single API. Configure OpenRouter as a provider in Janitor AI's settings with your API key.

What models work best with Janitor AI?

Janitor AI works with any model supported by its connected providers. Check individual model pages for VRAM requirements.

Janitor AI offers a free tier with limited features. Paid plans unlock higher usage limits and premium features.

← All apps

Janitor AI

Name: Janitor AI
Price: 9.99 USD

Chat Frontend Roleplay Creative

Cloud-based AI character roleplay platform. Largest character library, OpenRouter proxy support, and a massive 500K+ Discord community.

App type

Chat Frontend, Roleplay, Creative

Local models

Indirect

OpenRouter

Yes

Ollama

GPU required

No — runs in the cloud

Best for

Character roleplay with a massive community library

Setup difficulty

Easy

Platforms

Web

Pricing

Freemium

Janitor AI is Cloud-based AI character roleplay platform. Largest character library, OpenRouter proxy support, and a massive 500K+ Discord community. Janitor AI is a proprietary web-based chatbot platform focused on character roleplay and interactive fiction.

Janitor AI runs in the cloud via API providers. It supports OpenRouter for unified access to 300+ models from a single API. Janitor AI is a freemium product. No GPU required — all inference runs in the cloud. For advanced users connecting local inference servers (KoboldAI proxy): 6-8 GB VRAM for Pygmalion-class roleplay models.

Can it run on my hardware?

Janitor AI runs entirely in the cloud — no GPU required on your end. All AI inference happens on remote servers. You bring your own OpenRouter API key to access models.

You bring your own API keys for the AI providers you want to use.

App compatibility

Feature	Supported
Local models	No
OpenRouter	Yes
OpenAI-compatible API	Yes
Ollama	No
LM Studio	No
Anthropic API	Yes
Google API	No
Mistral API	No
Docker	No
Works offline	No
Needs GPU	No

Recommended models

Best cloud/API models

DeepSeek V3 671B

DeepSeek · 671B params · MoE

GLM-4.5 Air 106B

Z.ai · 106B params · MoE

Gemma 4 31B

Google · 31B params · Dense

GPT-OSS 120B

OpenAI · 117B params · MoE

Qwen3 235B-A22B (MoE)

Alibaba · 235B params · MoE

Local vs cloud: which should you use?

Use local models if

You want privacy — data never leaves your machine
You already have a GPU with sufficient VRAM
You want zero per-token API costs
You need offline access

Use cloud/API if

Your GPU has insufficient VRAM for the models you need
You want access to frontier model quality
You need maximum coding/reasoning performance
You don't want to manage local model downloads and updates
OpenRouter lets you switch between 300+ models with one API key

Setup overview

Setting up Janitor AI is straightforward. It runs on web.

Website →

Limitations

Privacy-sensitive use — cloud-only, not self-hostable
Local models — requires advanced KoboldAI proxy setup
General productivity (purpose-built for roleplay)
Free-tier users — JanitorLLM is weak, queue delays are long

Compatible models

DeepSeek V3 671B GLM-4.5 Air 106B Gemma 4 31B GPT-OSS 120B Qwen3 235B-A22B (MoE)

Frequently asked questions

What is Janitor AI?: Janitor AI is Cloud-based AI character roleplay platform. Largest character library, OpenRouter proxy support, and a massive 500K+ Discord community. Janitor AI is a proprietary web-based chatbot platform focused on character roleplay and interactive fiction.
Can Janitor AI use OpenRouter?: Yes. Janitor AI supports OpenRouter for accessing 300+ models through a single API. Configure OpenRouter as a provider in Janitor AI's settings with your API key.
What models work best with Janitor AI?: Janitor AI works with any model supported by its connected providers. Check individual model pages for VRAM requirements.
Is Janitor AI free?: Janitor AI offers a free tier with limited features. Paid plans unlock higher usage limits and premium features.