> ## Documentation Index
> Fetch the complete documentation index at: https://premlabs-fix-example-pdf.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Getting Started With The Prem API

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

<Card title="Prem Is Also OpenAI Compatible" icon="handshake" href="/get-started/quick-start">
  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`.

  Use our [Quickstart Guide](/get-started/quick-start) 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.

## 🚀 End-to-End Walkthroughs

New to Prem? Start here! These comprehensive walkthroughs guide you through complete workflows from data ingestion to fine-tuning, showing you how to use multiple API endpoints together.

<CardGroup cols={3}>
  <Card title="JSONL Dataset Workflow" icon="file-code" href="/api-reference/walkthroughs/jsonl-workflow">
    Upload a JSONL dataset, create snapshots, and launch fine-tuning jobs with your own data.
  </Card>

  <Card title="PDF Synthetic Workflow" icon="file-pdf" href="/api-reference/walkthroughs/pdf-synthetic-workflow">
    Generate synthetic Q\&A pairs from PDF documents and fine-tune models on corporate knowledge.
  </Card>

  <Card title="YouTube Synthetic Workflow" icon="video" href="/api-reference/walkthroughs/youtube-synthetic-workflow">
    Transform YouTube video content into training data and create specialized models.
  </Card>
</CardGroup>

***

## API Endpoints

#### Build your data pipeline

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

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

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

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

  <Card title="Fine-Tuning" icon="wrench" href="/api-reference/finetuning">
    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">
    Send prompts to deployed chat models
  </Card>

  <Card title="Models" icon="brain" href="/api-reference/models">
    List, load, and unload available models
  </Card>

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

### Authentication

All API endpoints are authenticated using Bearer tokens and picked up from the specification file.

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