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

# Getting Started

> Learn how to use the Sqwish API with basic examples

## Basic Usage

After setting your API key, you can optimize prompts easily. Here's a quick example showing how to optimize a prompt and inspect additional metadata returned by the API:

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    from sqwishai import Sqwish
    import os

    sqwish_client = Sqwish(os.environ.get("SQWISH_API_KEY"))

    input_prompt = "Write a haiku about recursion in programming."
    response = sqwish_client.text.optimize(input_prompt)
    ```
  </Tab>

  <Tab title="JavaScript">
    ```javascript theme={null}
    const { Sqwish } = require('sqwishai');
    const sqwishClient = new Sqwish(process.env.SQWISH_API_KEY);

    const inputPrompt = "Write a haiku about recursion in programming.";
    const response = sqwishClient.text.optimize(inputPrompt);
    ```
  </Tab>

  <Tab title="cURL">
    ```bash theme={null}
    curl -X POST "https://api.sqwish.ai/v1/optimization/optimize" \
      -H "Content-Type: application/json" \
      -H "Authorization: Bearer $SQWISH_API_KEY" \
      -d '{
        "text": "Write a haiku about recursion in programming.",
        "target_model": "gpt4o",
        "optimization_model": "latest"
    }'
    ```
  </Tab>
</Tabs>

## Response Format

The API returns a JSON response with the following structure:

```json theme={null}
{
  "message": "The optimized text prompt",
  "tokens_reduced": 150
}
```

Where:

* `message`: The optimized version of your input text
* `tokens_reduced`: Number of tokens saved by the optimization

## Advanced Usage

For more complex scenarios and direct REST API calls, see the [API Reference](/api-reference) section.