Workflow Icon

Brain Outsourcing

Chat with local and hosted LLMs

Version 26.1 by Alfred Team


Setup

Configure your desired LLM in the Workflow’s Configuration.

API Endpoint is the chat completions address specific to your service. Common values include:

Provider Endpoint
OpenAI/ChatGPT https://api.openai.com/v1/chat/completions
Anthropic/Claude https://api.anthropic.com/v1/chat/completions
Google/Gemini https://generativelanguage.googleapis.com/v1beta/openai/chat/completions
OpenRouter https://openrouter.ai/api/v1/chat/completions
Ollama http://localhost:11434/v1/chat/completions
LM Studio http://localhost:1234/v1/chat/completions
llama.cpp http://localhost:8080/v1/chat/completions

API Key is the unique identifier provided by the service to access your account. For local LLMs this can generally be left empty and a dummy key is used.

Model ID is the exact name of the model, which depends on your provider. They tend to closely follow the model name. For example:

Model Name Model ID
ChatGPT 5.4 Nano gpt-5.4-nano
Claude Opus 5.5 claude-opus-5-5
Llama 3.2 1B llama3.2:1b

Usage

Launch a UI to query an LLM via the chat keyword.

Start query

Querying

Configure the Hotkey for faster triggering.