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

# Getting Started With Prem API

> Learn how to interact with Prem's API endpoints.

<Card title="Prem Is Also OpenAI Compatible" icon="handshake" href="/get-started/sdks">
  Instead of using the Prem API, you can use the OpenAI SDK to generate chat completions with **Prem** by just changing the `base URL` and adding your `API key`.

  See our [Client SDKs guide](/get-started/sdks) to learn how to use [Prem AI](/index) with OpenAI's API/SDK.
</Card>

This is the **API Reference** for **Prem AI**.

Here you can find documentation for all of the endpoints that are available in the Prem API. You can use the sidebar to navigate to the different sections.

**Prem** provides a REST API that you can use to interact with the platform with any programming language that can make HTTP requests.

## API Endpoints

#### Build your data pipeline

<CardGroup cols={3}>
  <Card title="Projects" icon="folder" href="/api-reference/projects/post-projects-create">
    Provision and inspect project workspaces
  </Card>

  <Card title="Datasets" icon="database" href="/api-reference/datasets/post-datasets-create-from-jsonl">
    Ingest JSONL files or trigger synthetic runs
  </Card>

  <Card title="Snapshots" icon="scissors" href="/api-reference/snapshots/post-snapshots-create">
    Split datasets into train and validation sets
  </Card>

  <Card title="Recommendations" icon="sparkles" href="/api-reference/recommendations/post-recommendations-generate">
    Request model suggestions for a snapshot
  </Card>

  <Card title="Fine-Tuning" icon="wrench" href="/api-reference/finetuning/post-finetuning-create">
    Launch and monitor fine-tuning jobs
  </Card>
</CardGroup>

#### Run and observe models

<CardGroup cols={3}>
  <Card title="Chat Completions" icon="message" href="/api-reference/chat-completions/post-chatcompletions">
    Send prompts to deployed chat models
  </Card>

  <Card title="Models" icon="brain" href="/api-reference/models/get-models">
    List all available models
  </Card>

  <Card title="Traces" icon="rectangle-history" href="/api-reference/traces/post-traces">
    Retrieve traces captured during inference
  </Card>
</CardGroup>

### Authentication

All API endpoints are authenticated using Bearer tokens. You'll need to create an API key first - see our [API Key guide](/api-reference/api-key) for instructions.

Once you have your API key, include it in the `Authorization` header:

```bash theme={null}
Authorization: Bearer YOUR_API_KEY
```

The authentication is automatically picked up from the OpenAPI specification file:

```json theme={null}
"security": [
  {
    "bearerAuth": []
  }
]
```