Usar LetronnaLa appThe parts of the window
First start
The setup page the window shows when no model is connected yet.
Esta página aún no está traducida, así que se muestra en inglés. Puedes traducirla en GitHub. GitHub ↗
The first time you open the window, and whenever no model can be reached, it opens on a setup page. It has four steps, with a bar at the top for each. Back goes to the step before.
To set up from the terminal instead, see Getting started.
1. Welcome to Letronna
Press Get started.
2. Connect a model
Pick one way in. The others stay in Settings for later.
| Choice | What it is |
|---|---|
| Letronna account | hosted models, with free starter credit; charged to your credit |
| My own API key | OpenAI, Anthropic, OpenRouter, or any compatible server |
| On this computer | Ollama: works offline, no key |
- Letronna account: press Sign in in the browser. Your browser opens, and you come back here once you allow Letronna there.
- My own API key: the same gateway rows as Settings > Accounts. See Gateways.
- On this computer: Letronna looks for Ollama. If it is not found, install Ollama and it is picked up by itself.
Press Continue, or Skip for now.
3. Pick a model
New sessions start on it, and you can switch in any chat. Each model shows what it costs, in and out, per million tokens. More are in the model menu.
4. Where should it work?
Pick a project folder for its files and commands with Choose, or Change a folder you picked. Until you pick one, it works in Letronna's own folder in your home folder. You can change it any time, from the status bar.
Press Start using Letronna.
Set up Letronna, in the account menu in the top bar, brings this page back.