> ## Documentation Index
> Fetch the complete documentation index at: https://docs.simular.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GroundingModel

> A visual-language grounding model that can locate concepts on images.

## Constructor

```typescript
GroundingModel(): GroundingModel
```

### Returns

`GroundingModel`

## Properties

<ResponseField name={"name"} type={"string"} required>
  The wire-level model identifier sent in the request body.
</ResponseField>

## Methods

### availableAliases()

```typescript
availableAliases(): string[]
```

Every VLM model alias accepted by `byAlias` on this machine, deduplicated
and sorted alphabetically. Use to discover what aliases the loaded config
(bundled defaults plus any user provider files advertises.

#### Returns

`string[]`

### byAlias()

```typescript
byAlias(alias: string): GroundingModel
```

Resolve a model alias against the loaded config (e.g. `"ui_venus_30b"`,
`"ui_tars_7b"`, `"openrouter_claude_opus"`, or any alias declared by a
user provider). Throws if the alias is unknown.

#### Parameters

<ResponseField name={"alias"} type={"string"} required />

#### Returns

`GroundingModel`

### checkAuth()

```typescript
checkAuth(): void
```

Check that the API key works. Throws if it doesn't.

Call right after creating the model so a bad key fails fast,
before any UI automation has had a chance to steal focus:

```ts
try { model.checkAuth() } catch { process.exit(1) }
```

### default()

```typescript
default(): GroundingModel
```

First VLM model advertised by the first VLM provider in the loaded
configuration whose credentials are currently available. Providers with
missing credentials are skipped; throws if no provider remains available.

#### Returns

`GroundingModel`

### ground()

```typescript
ground(target: Image | Screenshot, concept: string): [number, number]
```

Locate `concept` on `target` and return zero-based pixel coordinates
`[x, y]`:

* If `target` is an `Image`, coordinates are in **image-space**.
* If `target` is a `Screenshot`, coordinates are in the **global desktop
  space** in OS-native units (may be negative on multi-monitor setups;
  see \[`Machine`]).

Equivalent to `target.ground(model, concept)`.

#### Parameters

<ResponseField name={"target"} type={"Image | Screenshot"} required />

<ResponseField name={"concept"} type={"string"} required />

#### Returns

`[number, number]`

### uiTars7B()

```typescript
uiTars7B(): GroundingModel
```

Convenience shim for the bundled `ui_tars_7b` alias. Throws if no
provider advertises that alias.

#### Returns

`GroundingModel`

### uiVenus30B()

```typescript
uiVenus30B(): GroundingModel
```

Convenience shim for the bundled `ui_venus_30b` alias. Throws if no
provider advertises that alias.

#### Returns

`GroundingModel`