# Get LLM Model

`GET /compute/llms/{modelId}` · Core · Compute & Automation

Retrieves metadata for a single LLM model by its identifier, including name, provider class, modality, token cost (per million input and output tokens), and supported parameters. Requires any Forge, Studio, or Workspace cohort role.

## Parameters

| Name | In | Required | Description |
|---|---|---|---|
| `modelId` | path | yes | The model's id, as the model list returns it. Example: `"mistral-7b"`. |
| `projectSlug` | path | yes | The project's slug: the path segment after `@`. It is unique within the org. Example: `"storefront"`. |

## Responses

- **200**: Success

| Field | Type | Required | Description |
|---|---|---|---|
| `data` | object | yes | A model in the project's model library. |
| `data.id` | string | yes | The model's id. Pass it as `modelId` to read or invoke the model. |
| `data.provider` | enum ("self_hosted", "anthropic", "openai") | yes | Who serves the model. `self_hosted`: the platform runs it. `anthropic` or `openai`: the outside provider, called with the project's own key. |
| `data.providerClass` | enum ("platform", "tenant_key") | yes | platform: run and billed by the platform. tenant_key: called with the project's own provider key and billed by that provider. |
| `data.modality` | enum ("text_completion", "text_completion_with_tools", "embeddings") | yes | What the model does. `text_completion`: generates text. `text_completion_with_tools`: generates text and can call tools. `embeddings`: turns text into vectors. |
| `data.invocable` | boolean | yes | Whether this model can be invoked through the platform. |
| `data.reason` | enum ("tenant_key_only") | no | Present only when invocable is false. |
| `data.priceIn` | object | yes | US dollars per 1M input tokens (embedding tokens for an embeddings model). Null for a tenant_key model or when no rate is set. |
| _one of_ | | |  |
| _or_ | | |  |
| `data.priceOut` | object | yes | US dollars per 1M output tokens. Null for an embeddings model, a tenant_key model, or when no rate is set. |
| _one of_ | | |  |
| _or_ | | |  |
| `data.priceUnit` | enum ("usd_per_million_tokens") | yes | The unit of `priceIn` and `priceOut`: always US dollars per million tokens. |
| `meta` | object | yes |  |


## Errors

| HTTP | Code | When |
|---|---|---|
| 401 | `K9O_INVALID_CREDENTIALS` | The request credentials are missing or invalid. |
| 401 | `K9O_SESSION_EXPIRED` | Your session has expired; sign in again to continue. |
| 403 | `K9O_ACCESS_DENIED` | Your role does not grant access to read model metadata for this project. |
| 400 | `K9O_MODEL_NOT_DECLARED` | The requested model ID is not in the supported model catalogue. |

## Code samples

### cURL

```bash
curl -X GET 'https://<org>.api-<region>.k9o.io/@storefront/compute/llms/<modelId>' \
  -H 'Authorization: Bearer $K9O_TOKEN'
```

### fetch

```javascript
const res = await fetch('https://<org>.api-<region>.k9o.io/@storefront/compute/llms/<modelId>', {
  method: 'GET',
  headers: {
    'Authorization': `Bearer ${process.env.K9O_TOKEN}`
  },
});
const { data, meta } = await res.json();
```

### @k9o/core

```typescript
// const k9o = new K9o({ orgSlug: 'playground', projectSlug: 'storefront', apiKey: 'k9o_…' })
const { data } = await k9o.compute.llms.read('mistral-7b')
```

### k9o

```python
# k9o = create_client(org_slug="playground", project_slug="storefront", api_key="k9o_…")
response = k9o.compute.llms.read("mistral-7b")
```

### sdk-go

```go
// ctx := context.Background()
// client, _ := k9o.NewClient(k9o.ClientOpts{OrgSlug: "playground", ProjectSlug: "storefront", APIKey: "k9o_…"})
data, _, kerr := client.Compute.Llms.Read(ctx, "mistral-7b")
```

### k9o

```rust
// let k9o = Client::new(ClientOpts { org_slug: "playground".into(), project_slug: "storefront".into(), api_key: "k9o_…".into() })?;
let resp = k9o.compute.llms.read("mistral-7b").await?
```

### dev.k9o:core

```java
// K9o k9o = K9o.createClient(K9o.Opts.builder().orgSlug("playground").projectSlug("storefront").apiKey("k9o_…").build());
var response = k9o.compute().llms().read("mistral-7b")
```

### K9o.Core

```c#
// var k9o = K9oClient.Create(new K9oOptions { OrgSlug = "playground", ProjectSlug = "storefront", ApiKey = "k9o_…" });
var response = await k9o.Compute.Llms.ReadAsync("mistral-7b")
```

### k9o

```ruby
# k9o = K9o.create_client(org_slug: "playground", project_slug: "storefront", api_key: "k9o_…")
response = k9o.compute.llms.read("mistral-7b")
```

### k9o/sdk

```php
// $k9o = K9oClient::create(['org_slug' => 'playground', 'project_slug' => 'storefront', 'api_key' => 'k9o_…']);
$response = $k9o->compute->llms->read('mistral-7b')
```


Canonical page: https://docs.kilimanjaro.dev/api-playground/core/get-llm-model
