Cloud AI Providers
RTILA X supports cloud AI providers for when you need more powerful models or don’t want to run models locally.
OpenRouter (Recommended)
Section titled “OpenRouter (Recommended)”OpenRouter gives you access to hundreds of AI models through a single API key.
- Go to Preferences → AI Assistant tab.
- Set AI Provider to OpenRouter.
- Enter your OpenRouter API key in the API Key field.
- Choose a model from the dropdown or enter a custom model name.
Getting an OpenRouter API Key
Section titled “Getting an OpenRouter API Key”- Go to openrouter.ai/keys.
- Sign up or log in.
- Click Create Key.
- Copy the key and paste it into RTILA X.
Available Models
Section titled “Available Models”Popular models available through OpenRouter:
| Model | Description |
|---|---|
google/gemini-3.1-flash-lite-preview |
Fast, lightweight (default) |
google/gemini-3-flash-preview |
Fast with good quality |
google/gemini-2.5-flash |
Balanced speed and quality |
google/gemini-2.5-flash-lite |
Very fast |
anthropic/claude-sonnet-4.5 |
High quality |
x-ai/grok-4.1-fast |
Fast with reasoning |
moonshotai/kimi-k2.5 |
Good for long context |
minimax/minimax-m2.5 |
Efficient |
z-ai/glm-5 |
Open-source option |
arcee-ai/trinity-large-preview:free |
Free tier option |
Custom Model Names
Section titled “Custom Model Names”You can enter any OpenRouter model name in the model field, even if it’s not in the dropdown. Use the Verify button to check if a model name is valid.
Custom Provider (OpenAI-Compatible)
Section titled “Custom Provider (OpenAI-Compatible)”For self-hosted models (e.g., Ollama, LM Studio, vLLM):
- Set AI Provider to Custom Provider.
- Enter the API Base URL (e.g.,
http://localhost:11434/v1). - Enter an API Key (optional for local servers).
- Enter the Model Name (e.g.,
llama3.1).
Common Local Server URLs
Section titled “Common Local Server URLs”| Server | Base URL |
|---|---|
| Ollama | http://localhost:11434/v1 |
| LM Studio | http://localhost:1234/v1 |
| vLLM | http://localhost:8000/v1 |
| text-generation-webui | http://localhost:5000/v1 |
RAG (Retrieval-Augmented Generation)
Section titled “RAG (Retrieval-Augmented Generation)”When using cloud providers or custom models, RTILA X automatically enables RAG (Retrieval-Augmented Generation). This allows the AI to search a local knowledge base for relevant training data.
See RAG Knowledge Base for details.