# Models

Choose which AI models your bots think with, using your own subscription, your own API key, or a
model you run yourself.

## Connect a provider

Open **Settings → Models**. Under **Add provider**, pick a provider and connect it:

- **Sign in** with a ChatGPT or Claude subscription to use the plan you already pay for.
- **Connect API key** for OpenAI, Anthropic, Google, OpenRouter and many others.
- **OpenAI-compatible server URL** for a model you host yourself, such as Ollama or vLLM on your own
  machine. Paste the address, choose **Find models**, and pick one. Under **Advanced** you can set
  its context limit, whether it supports images, and its reasoning effort.

Connected providers are listed under **Providers** and are available in every [space](/docs/spaces/).

> [!NOTE]
> On Opisense Cloud you can skip this: bots run on Opisense's model with your plan's allowance and
> credits. Your own provider needs a paid plan there, and runs on it don't use your allowance. See
> [Account and billing](/docs/account/#billing-on-opisense-cloud).

## Main model and fallbacks

**Main model** is what every bot uses unless you choose otherwise. Choose **Add fallback** to list
backup models; if the main model fails or hits a limit, the bot moves to the next one. **Move up**
and **Move down** set the order.

Each model has a **Thinking** level, from **Minimal** to **Max**. Higher thinking is slower and
costs more, and helps on hard, multi-step work.

## Pick a model

- Get a new bot's job right on a strong model first, then try a faster, cheaper one for routine
  work such as a daily check or sorting mail. Keep the strong one for research, writing and
  multi-step work.
- A bot that uses its computer's screen needs a model that can read images.
- Keep **Thinking** low for quick replies, and raise it for planning and hard problems.
- Add a fallback from a different provider, so one provider's outage doesn't stop your bots.
- After a week, compare what each bot costs in **Settings → Usage**.

## Approval model

**Approval model** is the model that checks bot actions when approvals are set to **Auto review**.
A fast, inexpensive model works well here. See [Approvals](/docs/approvals/).

## Per bot and per routine

To give one bot a different model, open its settings, expand **Advanced**, and choose its **Model**
and **Thinking**. A [routine](/docs/routines/) can also have its own model, for example a cheaper one
for a simple daily check.

> [!TIP]
> Bots that use the computer's screen need a model that can read images. Models that can't are
> marked **Can't read images** in the picker.

## Usage

**Settings → Usage** shows cost, tokens and runs per day, broken down by model, bot or activity. See
[Account and billing](/docs/account/#usage).
