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

# read

> URL to clean text — articles, docs, pages

The `read` capability extracts clean, readable text from URLs. It handles JavaScript rendering, removes navigation and ads, and returns the main content.

## Providers

| Provider  | Features               |
| --------- | ---------------------- |
| Jina      | Fast, clean extraction |
| Firecrawl | Handles complex pages  |

## Basic Usage

```typescript theme={null}
const result = await saturn.read({
  url: 'https://example.com/article',
});

console.log(result.data.content);
// → Clean text content without HTML, ads, or navigation
```

## Parameters

<ParamField body="url" type="string" required>
  The URL to read content from.
</ParamField>

<ParamField body="provider" type="string">
  Specific provider to use (`jina` or `firecrawl`).
</ParamField>

## Response

```typescript theme={null}
interface ReadResponse {
  data: {
    content: string;    // Extracted text content
    title: string;      // Page title
    url: string;        // Final URL (after redirects)
  };
  metadata: {
    chargedUsdCents: number;
    provider: string;
    latencyMs: number;
    auditId: string;
  };
}
```

## Examples

### Read and Summarize

```typescript theme={null}
const page = await saturn.read({
  url: 'https://blog.example.com/long-article',
});

const summary = await saturn.reason({
  prompt: `Summarize this article:\n\n${page.data.content}`,
  maxTokens: 500,
});

console.log(summary.data.content);
```

### Research Pipeline

```typescript theme={null}
async function researchTopic(query: string) {
  // Find relevant pages
  const search = await saturn.search({ query, numResults: 5 });

  // Read all pages in parallel
  const pages = await Promise.all(
    search.data.results.map(r => saturn.read({ url: r.url }))
  );

  // Extract key information
  const synthesis = await saturn.reason({
    prompt: `Based on these sources, summarize what we know about "${query}":\n\n${
      pages.map((p, i) => `Source ${i + 1}: ${p.data.content.slice(0, 3000)}`).join('\n\n')
    }`,
  });

  return synthesis.data.content;
}
```

## When to Use `read` vs `scrape`

| Capability | Use case                            | Returns    |
| ---------- | ----------------------------------- | ---------- |
| `read`     | Articles, blog posts, documentation | Clean text |
| `scrape`   | Data extraction, structured content | Raw HTML   |

Use `read` when you want the **content**. Use `scrape` when you need the **structure**.

## Pricing

| Provider  | Cost per page |
| --------- | ------------- |
| Jina      | \~\$0.001     |
| Firecrawl | \~\$0.002     |

## Error Handling

```typescript theme={null}
try {
  const page = await saturn.read({ url: 'https://example.com/article' });
} catch (err) {
  if (err.code === 'PROVIDER_ERROR') {
    // Page couldn't be read (404, blocked, etc.)
    console.log('Could not read page:', err.message);
  }
}
```