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

# Tailor Your Search

For an LLM or agent, search is the bridge to everything that happened after training: the live web, today's facts, the newest sources.

Octen Search is built to be that bridge. It gives a model fresh, relevant content from the live web to ground its answers on.

This guide walks through the scenarios it covers and the options that tailor it to each.

For the full list, see the [Web Search API reference](/api-reference/search).

## Why Octen

* **Fresh.** A minute-fresh index keeps fast-moving facts current: live stock and crypto prices, sports scores, breaking news, product launches, and just-published releases.
* **Fast.** Average latency as low as 62ms, quick enough to stay in the loop.
* **Accurate.** Built on SOTA models, top-ranked on multiple search benchmarks. Returns search results with relevant highlights and optional full content.
* **Comprehensive.** Broad coverage of the web, with optional images and videos alongside the results. Filter by topic, domain, text, and time to focus on exactly what you need.

## Scenarios

### Real-time data

Live stock and crypto prices, sports scores, exchange rates. Octen indexes fast-moving data in real time.

```bash theme={null}
curl -X POST https://api.octen.ai/search \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "query": "Tesla stock price"
  }'
```

### Breaking news

For current events and the latest headlines, focus on recent, news-sourced pages.

```json theme={null}
{
  "query": "latest on the climate summit",
  "topic": "news",
  "time_range": "day"
}
```

* `topic: "news"` focuses on news sources, where event coverage is richest.
* `time_range: "day"` keeps results from the last 24 hours; widen to `"week"` for slower-moving stories.

### Full page content

When you need the original text of each page, turn on full content.

```json theme={null}
{
  "query": "standing desk ergonomics guidelines",
  "count": 8,
  "full_content": { "enable": true, "max_tokens": 4000 }
}
```

* `full_content.enable: true` returns the clean full text of each page.
* Highlights stay on by default, giving you a short, query-relevant snippet of each page.

### Limit or steer your sources

Constrain results to sites you trust, or require certain terms to appear on the page.

```json theme={null}
{
  "query": "central bank interest rate decision",
  "include_domains": ["reuters.com", "bloomberg.com"],
  "exclude_domains": ["medium.com"],
  "include_text": ["interest rate"],
  "exclude_text": ["opinion"]
}
```

* `include_domains` / `exclude_domains` allow or block specific sites.
* `include_text` / `exclude_text` require or forbid specific words in the page text.

### Include images and videos

Return media alongside the text results, useful for news coverage and rich previews.

```json theme={null}
{
  "query": "northern lights tonight",
  "topic": "news",
  "include_images": true,
  "include_videos": true
}
```

## Parameter cheatsheet

| Parameter                             | Default   | Change it when                                                       |
| ------------------------------------- | --------- | -------------------------------------------------------------------- |
| `topic`                               | `general` | Set `news` for current events, live scores, and breaking stories.    |
| `count`                               | `5`       | Raise (up to `100`) for more recall; lower for just the top sources. |
| `time_range`                          | —         | Set `day` / `week` / `month` / `year` to keep results recent.        |
| `start_time` / `end_time`             | —         | Bound results to a specific date range.                              |
| `highlight.max_tokens`                | `512`     | Raise for longer relevant passages; lower to save tokens.            |
| `full_content`                        | `false`   | Enable to get the full page text.                                    |
| `format`                              | `text`    | Set `markdown` to return highlights as markdown.                     |
| `include_domains` / `exclude_domains` | —         | Allow or block specific sites.                                       |
| `include_text` / `exclude_text`       | —         | Require or forbid words in the page text.                            |
| `include_images` / `include_videos`   | `false`   | Return media with each result.                                       |
| `safesearch`                          | `strict`  | Set `off` to disable adult-content filtering.                        |