llm-models
inference-sh6 installs
Get answers from 100+ models with one CLI.
What it does
Runs prompts against a choice of hosted language models and returns generated responses through one CLI.
When to use it
Use for coding, writing, analysis, AI workflows, and conversational interfaces.
How to use it
Give it a prompt; it calls a hosted language model through the CLI to obtain a response.
What you provide
- a prompt
Uses
Good to know
- edits its own instructions
Latest review
What you need · 3
Requires the inference.sh CLI, whose binary is belt.
Requires signing in through belt before calling a model.
Access · 2
This skill
inference.sh
Write
Sends prompts to hosted models
npx skills add belt-sh/cli
Execute
Installs the belt CLI skill