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

# Getting Started

> EigenAI is a high-performance platform for model inference, fine-tuning, and deployment.

EigenAI gives you access to state-of-the-art language, vision, image, and audio models through an OpenAI-compatible API — and lets you fine-tune and deploy your own models on the same infrastructure.

## Quickstart

Make your first API call in three steps.

<Steps>
  <Step title="Get an API key">
    Go to [API Keys](https://app.eigenai.com/api-keys) in the EigenAI dashboard and create a key.
  </Step>

  <Step title="Choose a model">
    Browse the [Model Library](https://app.eigenai.com/model-library) and copy the model ID you want to use.
  </Step>

  <Step title="Make a request">
    Call the Chat Completions endpoint:

    <CodeGroup>
      ```bash cURL theme={null}
      curl -X POST https://api-web.eigenai.com/api/v1/chat/completions \
        -H "Authorization: Bearer YOUR_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{
          "model": "YOUR_MODEL_ID",
          "messages": [
            {"role": "user", "content": "Hello!"}
          ]
        }'
      ```

      ```python Python theme={null}
      from openai import OpenAI

      client = OpenAI(
          api_key="YOUR_API_KEY",
          base_url="https://api-web.eigenai.com/api/v1"
      )

      response = client.chat.completions.create(
          model="YOUR_MODEL_ID",
          messages=[{"role": "user", "content": "Hello!"}]
      )
      print(response.choices[0].message.content)
      ```
    </CodeGroup>
  </Step>
</Steps>

## What do you want to do?

<CardGroup cols={2}>
  <Card title="Call a model" icon="bolt" href="/products/model-api/api-reference/base-url">
    Use the OpenAI-compatible API to run chat, vision, image generation, video, and audio models.
  </Card>

  <Card title="Fine-tune a model" icon="sliders" href="/platform/fine-tuning">
    Train a base model on your own dataset using SFT, Image Editing, or RL.
  </Card>

  <Card title="Deploy a model" icon="server" href="/platform/deployments">
    Provision a dedicated GPU endpoint for any supported or fine-tuned model.
  </Card>

  <Card title="Generate training data" icon="database" href="/products/eigendata-cli/intro">
    Use the EigenData CLI to generate, modify, and analyze structured datasets.
  </Card>
</CardGroup>