> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Openperplex

> Openperplex API provides powerful, global search capabilities and web content analysis for AI applications.

![Openperplex logo](https://mintcdn.com/composio-preview/gqjBKmmJCINafaiK/images/toolkits/openperplex.svg?fit=max\&auto=format\&n=gqjBKmmJCINafaiK\&q=85\&s=3c2b8068b860b7fa9763fec5b34c76b1)

* **Category:** web search & research
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 8
* **Triggers:** 0
* **Slug:** `OPENPERPLEX`
* **Version:** 20261101\_00

## Tools

> [accordion] Custom Search
>
> **Slug:** `OPENPERPLEX_CUSTOM_SEARCH`
>
> Tool to perform a custom search with optional filtering and field selection. Use when you need tailored results based on query, filters, size, or fields.
>
> #### Input Parameters
>
> **size** `integer`
>
> Number of desired results (must be ≥ 1).
>
> **query** `string` *required*
>
> The search query string.
>
> **filter** `object`
>
> Filters to apply on the search results.
>
> **user\_prompt** `string` *required*
>
> User prompt for guiding the search.
>
> **system\_prompt** `string` *required*
>
> System prompt for guiding the search.
>
> **exclude\_fields** `array`
>
> Fields to exclude from results.
>
> **include\_fields** `array`
>
> Fields to include in results.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Custom Search Stream
>
> **Slug:** `OPENPERPLEX_CUSTOM_SEARCH_STREAM`
>
> Tool to perform custom streaming search with custom prompts. Use when you need AI-powered search responses with custom system and user prompts for more specific or tailored queries. Returns aggregated text response along with optional sources and images.
>
> #### Input Parameters
>
> **model** `string`
>
> Model to use for the search. Options: 'gpt-4o-mini' (default), 'gpt-4o', 'o3-mini-high', 'o3-mini-medium', 'gemini-2.0-flash'.
>
> **top\_p** `number`
>
> Top-p for output diversity (0.0-1.0, default 0.9).
>
> **location** `string`
>
> Two-letter country code for localized results, e.g., 'us', 'uk', 'fr', 'de', 'jp'.
>
> **search\_type** `string ("general" | "news")`
>
> Type of search: 'general' or 'news'.
>
> **temperature** `number`
>
> Temperature for output randomness (0.0-1.0 exclusive, default 0.2).
>
> **user\_prompt** `string` *required*
>
> User prompt specifying the search query. Be specific as this is used for web search.
>
> **return\_images** `boolean`
>
> Whether to include images in the response.
>
> **system\_prompt** `string` *required*
>
> System prompt defining assistant behavior and response format.
>
> **recency\_filter** `string ("hour" | "day" | "week" | "month" | "year" | "anytime")`
>
> Filter results by recency: 'hour', 'day', 'week', 'month', 'year', or 'anytime'.
>
> **return\_sources** `boolean`
>
> Whether to include sources in the response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Website Markdown
>
> **Slug:** `OPENPERPLEX_GET_WEBSITE_MARKDOWN`
>
> Tool to retrieve the markdown content of a specified website. Use after confirming the URL. Supports optional formats like 'gfm' or 'commonmark'.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The full URL of the website to fetch and convert to markdown
>
> **markdown\_format** `string ("gfm" | "commonmark")`
>
> The target markdown standard/format
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Website Screenshot
>
> **Slug:** `OPENPERPLEX_GET_WEBSITE_SCREENSHOT`
>
> Tool to capture a screenshot of a website. Use after confirming the target URL is reachable.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The website URL to capture.
>
> **full\_page** `boolean`
>
> Whether to capture the entire scrollable page.
>
> **viewport\_width** `integer`
>
> Width of the browser viewport in pixels.
>
> **viewport\_height** `integer`
>
> Height of the browser viewport in pixels.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Website Text
>
> **Slug:** `OPENPERPLEX_GET_WEBSITE_TEXT`
>
> Tool to retrieve the main text content of a specified website URL. Use when you need content extraction from online articles or pages. Use after confirming the URL is publicly accessible.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The URL of the web page to extract text from.
>
> **clean** `boolean`
>
> If true, returns cleaner and more concise text.
>
> **max\_length** `integer`
>
> Maximum number of characters to extract.
>
> **return\_type** `string ("plain" | "html" | "markdown")`
>
> Format of the returned text: 'plain', 'html', or 'markdown'.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Query from URL
>
> **Slug:** `OPENPERPLEX_QUERY_FROM_URL`
>
> Tool to query documents from a URL. Use when you need to fetch and interrogate web-hosted content with a natural language question.
>
> #### Input Parameters
>
> **url** `string` *required*
>
> The URL of the website you want to interact with.
>
> **model** `string`
>
> LLM model to use. Options: o3-mini-high, o3-mini-medium, gpt-4o, gpt-4o-mini, gemini-2.0-flash. Default is gpt-4o-mini.
>
> **query** `string` *required*
>
> The question you want to ask about the content at the URL.
>
> **answer\_type** `string ("text" | "markdown" | "html")`
>
> Format of the answer. Options: 'text', 'markdown', or 'html'. Default is 'text'.
>
> **response\_language** `string`
>
> Language code for the response. 'auto' will auto-detect based on the query. Supported: auto, en, fr, es, de, it, pt, nl, ja, ko, zh, ar, ru, tr, hi.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Documents
>
> **Slug:** `OPENPERPLEX_SEARCH`
>
> Tool to search documents using query parameters. Use when you have a search query and optional filters ready.
>
> #### Input Parameters
>
> **model** `string`
>
> Model to use for generating responses. Options: 'o3-mini-high', 'o3-mini-medium', 'gpt-4o', 'gpt-4o-mini', 'gemini-2.0-flash'.
>
> **query** `string` *required*
>
> The search query or question you want to ask. This is the primary input for your search.
>
> **location** `string`
>
> Country code for localized search results (e.g., 'us', 'jp', 'br', 'fr').
>
> **answer\_type** `string ("text" | "markdown" | "html")`
>
> Format of the answer. Options: 'text', 'markdown', or 'html'.
>
> **search\_type** `string ("general" | "news")`
>
> Type of search to perform. Options: 'general' or 'news'.
>
> **date\_context** `string`
>
> Optional date for context. Format example: 'Today is Monday 16 of September 2024 and the time is 6:36 PM'. If not provided, the API uses the current date of the server.
>
> **return\_images** `boolean`
>
> Set to True to include images in the result.
>
> **recency\_filter** `string ("hour" | "day" | "week" | "month" | "year" | "anytime")`
>
> Filter results by recency. Options: 'hour', 'day', 'week', 'month', 'year', 'anytime'.
>
> **return\_sources** `boolean`
>
> Set to True to include sources in the result.
>
> **return\_citations** `boolean`
>
> Set to True to include citations in the response.
>
> **response\_language** `string`
>
> Language code for the response. Use 'auto' to auto-detect based on the query.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Stream
>
> **Slug:** `OPENPERPLEX_SEARCH_STREAM`
>
> Search OpenPerplex using a query and return an aggregated AI-generated text response, with optional sources, images, and citations.
>
> #### Input Parameters
>
> **model** `string`
>
> Model to use for the search. Options: 'gpt-4o-mini' (default), 'gpt-4o', 'o3-mini-high', 'o3-mini-medium', 'gemini-2.0-flash'.
>
> **query** `string` *required*
>
> Search query string.
>
> **location** `string`
>
> Two-letter country code for localized results, e.g., 'us', 'uk', 'fr', 'de', 'jp'.
>
> **answer\_type** `string ("text" | "markdown" | "html")`
>
> Format of the answer: 'text', 'markdown', or 'html'.
>
> **search\_type** `string ("general" | "news")`
>
> Type of search: 'general' or 'news'.
>
> **date\_context** `string`
>
> Optional date context string, e.g., 'Today is Monday 16 of September 2024 and the time is 6:36 PM'. Uses server date if not provided.
>
> **return\_images** `boolean`
>
> Whether to include images in the response.
>
> **recency\_filter** `string ("hour" | "day" | "week" | "month" | "year" | "anytime")`
>
> Filter results by recency: 'hour', 'day', 'week', 'month', 'year', or 'anytime'.
>
> **return\_sources** `boolean`
>
> Whether to include sources in the response.
>
> **return\_citations** `boolean`
>
> Whether to include citations in the response.
>
> **response\_language** `string`
>
> Language code for response. 'auto' auto-detects based on query. Options: en, fr, es, de, it, pt, nl, ja, ko, zh, ar, ru, tr, hi.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
