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

# Quickstart

> Make your first Kyara Intelligence API call in under a minute. Create a key, pick a model, and send a chat completions request.

This quickstart takes you from zero to your first response from the Kyara Intelligence API. By the end you'll have a working API key, a model, and a successful chat completions call, all in under a minute.

<Steps>
  <Step title="Create an API key">
    Open the [Kyara dashboard](https://kyara-intelligence.com/dashboard) and create a new API key. The key is shown only once, so copy it immediately and store it somewhere safe.

    Set it as an environment variable so you never have to hard-code it:

    ```bash theme={null}
    export KYARA_INTELLIGENCE_API_KEY="your-api-key-here"
    ```
  </Step>

  <Step title="Choose a model">
    Browse the [model catalog](https://kyara-intelligence.com/models) and copy the ID of the model you want to use. This guide uses `deepseek/deepseek-v4-flash` as a fast, low-cost default. Swap in any other model ID whenever you like.
  </Step>

  <Step title="Send a request">
    Point your client at the Kyara base URL (`https://api.kyara-intelligence.com/v1`) and call the chat completions endpoint. If you're using the JavaScript or Python OpenAI SDK, install it first:

    * **JavaScript:** `npm install openai`
    * **Python:** `pip install openai`

    Then send your first request:

    <CodeGroup>
      ```bash curl theme={null}
      curl https://api.kyara-intelligence.com/v1/chat/completions \
        -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{
          "model": "deepseek/deepseek-v4-flash",
          "messages": [
            { "role": "user", "content": "Hello!" }
          ]
        }'
      ```

      ```javascript JavaScript theme={null}
      import OpenAI from "openai";

      const client = new OpenAI({
        baseURL: "https://api.kyara-intelligence.com/v1",
        apiKey: process.env.KYARA_INTELLIGENCE_API_KEY,
      });

      const response = await client.chat.completions.create({
        model: "deepseek/deepseek-v4-flash",
        messages: [{ role: "user", content: "Hello!" }],
      });

      console.log(response.choices[0].message.content);
      ```

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

      client = OpenAI(
          base_url="https://api.kyara-intelligence.com/v1",
          api_key=os.environ.get("KYARA_INTELLIGENCE_API_KEY"),
      )

      response = client.chat.completions.create(
          model="deepseek/deepseek-v4-flash",
          messages=[{"role": "user", "content": "Hello!"}],
      )

      print(response.choices[0].message.content)
      ```
    </CodeGroup>

    <Tip>
      Any OpenAI-compatible SDK works with the same base URL, not just the official `openai` package. If your tool lets you set a base URL, Kyara works with it.
    </Tip>
  </Step>
</Steps>

## What's next

<CardGroup cols={2}>
  <Card title="API Reference" icon="code" href="/api/chat-completions">
    Explore the full chat completions request schema, response format, and streaming.
  </Card>

  <Card title="SillyTavern" icon="wand-magic-sparkles" href="/integrations/sillytavern">
    Connect the SillyTavern frontend to Kyara Intelligence in a few steps.
  </Card>
</CardGroup>