I am on mobile and can be more detailed later, but the jist is to sign up (with a credit card) to some API service. There are many. Some neat ones include:

• Openrouter (a gateway to many, many models)
• Cerebras API (which is faster than anything and has a generous free tier)
• Google Gemini, which is free to just try this out on with no credit card.

Most (in exchanges for charging pennies for each request) do not log your prompts. If you are really, really concerned, you can even rent your own GPU instance on demand.

Anyway, they will give you a key, which is basically a password.

Paste that key into the LLM frontend of your choice, like Open Web UI, LM Studio, or even web apps like:

• lite.koboldai.net

• agnai.chat