AI agents: this page is for people. Read https://agentmarket.fluxapay.xyz/marketplace/apis/tavily/skills.md for every endpoint, its price, and how to call it with a FluxA API key (no account with Tavily needed).

TavilyVerified
Tavily web access built for AI agents: live web search with ranked results, snippets and optional…
Tavily web access built for AI agents: live web search with ranked results, snippets and optional LLM answers (basic or advanced depth), clean page extraction from URLs, site mapping and full-site crawling. Priced at Tavily's own per-credit rate, no Tavily account needed.
Ask your agent, for example
Copy one and give it to Claude Code, Codex or any agent:
Your agent will ask for your FluxA API key.
Endpoints 7All 7 healthy
https://router.fluxapay.xyz/api/tavilyCopy base URLCrawl a website from a root URL and return each page's content (basic extraction), with depth/breadth limits and path/domain regex filters. $0.0024 per page, billed on limit (default 50, max 100).
$0.0024 per page; set limit (default 50, max 100)
| Parameter | Type | Required | What it is |
|---|---|---|---|
url | string | Required | The root URL to begin the crawl. |
max_depth | integer | Optional | Max depth of the crawl. Defines how far from the base URL the crawler can explore. Default 1. Max 5. |
max_breadth | integer | Optional | Max number of links to follow per level of the tree (i.e., per page). Default 20. Max 500. |
limit | integer | Optional | Max pages crawled (you pay per page up to this). Default 50, max 100. |
select_paths | array | Optional | Regex patterns to select only URLs with specific path patterns (e.g., `/docs/.*`, `/api/v1.*`). |
select_domains | array | Optional | Regex patterns to select crawling to specific domains or subdomains (e.g., `^docs\.example\.com$`). |
exclude_paths | array | Optional | Regex patterns to exclude URLs with specific path patterns (e.g., `/private/.*`, `/admin/.*`). |
exclude_domains | array | Optional | Regex patterns to exclude specific domains or subdomains from crawling (e.g., `^private\.example\.com$`). |
allow_external | boolean | Optional | Whether to include external domain links in the final results list. Default true. |
include_images | boolean | Optional | Whether to include images in the crawl results. Default false. |
format | string | Optional | The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency. One of: markdown, text. Default "markdown". |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
timeout | number | Optional | Maximum time in seconds to wait for the crawl operation before timing out. Must be between 10 and 150 seconds. Default 150. Max 150. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. `NOTE:`The value may be 0 if the total use of /extract and /map have not yet reached minimum requirements. See our Credits & Pricing documentation for details. Default false. |
Crawl a website from a root URL and return each page's content (advanced extraction), with depth/breadth limits and path/domain regex filters. $0.0040 per page, billed on limit (default 50, max 100).
$0.004 per page; set limit (default 50, max 100)
| Parameter | Type | Required | What it is |
|---|---|---|---|
url | string | Required | The root URL to begin the crawl. |
max_depth | integer | Optional | Max depth of the crawl. Defines how far from the base URL the crawler can explore. Default 1. Max 5. |
max_breadth | integer | Optional | Max number of links to follow per level of the tree (i.e., per page). Default 20. Max 500. |
limit | integer | Optional | Max pages crawled (you pay per page up to this). Default 50, max 100. |
select_paths | array | Optional | Regex patterns to select only URLs with specific path patterns (e.g., `/docs/.*`, `/api/v1.*`). |
select_domains | array | Optional | Regex patterns to select crawling to specific domains or subdomains (e.g., `^docs\.example\.com$`). |
exclude_paths | array | Optional | Regex patterns to exclude URLs with specific path patterns (e.g., `/private/.*`, `/admin/.*`). |
exclude_domains | array | Optional | Regex patterns to exclude specific domains or subdomains from crawling (e.g., `^private\.example\.com$`). |
allow_external | boolean | Optional | Whether to include external domain links in the final results list. Default true. |
include_images | boolean | Optional | Whether to include images in the crawl results. Default false. |
format | string | Optional | The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency. One of: markdown, text. Default "markdown". |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
timeout | number | Optional | Maximum time in seconds to wait for the crawl operation before timing out. Must be between 10 and 150 seconds. Default 150. Max 150. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. `NOTE:`The value may be 0 if the total use of /extract and /map have not yet reached minimum requirements. See our Credits & Pricing documentation for details. Default false. |
Extract clean markdown or text from web pages (basic depth). Optional query reranks chunks. $0.0016 per URL, up to 20 per call.
$0.0016 per url; one per item in urls (max 20, extra items are dropped)
| Parameter | Type | Required | What it is |
|---|---|---|---|
urls | array | Required | URLs to extract, e.g. ["https://en.wikipedia.org/wiki/Artificial_intelligence"]. Max 20 per call; extras are dropped. Failed URLs are not billed by Tavily. |
query | string | Optional | User intent for reranking extracted content chunks. When provided, chunks are reranked based on relevance to this query. |
chunks_per_source | integer | Optional | Chunks are short content snippets (about 800 characters each) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `raw_content` length. Chunks will appear in the `raw_content` field as: `<chunk 1> [...]... Default 3. Max 5. |
include_images | boolean | Optional | Include a list of images extracted from the URLs in the response. Default is false. Default false. |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
format | string | Optional | The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency. One of: markdown, text. Default "markdown". |
timeout | number | Optional | Maximum time in seconds to wait for the URL extraction before timing out. Must be between 1.0 and 60.0 seconds. If not specified, default timeouts are applied based on extract_depth: 10 seconds for basic extraction and 30 seconds for advanced extraction. Default "None". Max 60.0. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. `NOTE:`The value may be 0 if the total successful URL extractions has not yet reached 5 calls. See our Credits & Pricing documentation for details. Default false. |
Extract clean markdown or text from web pages (advanced depth, incl. tables and embedded content). Optional query reranks chunks. $0.0032 per URL, up to 20 per call.
$0.0032 per url; one per item in urls (max 20, extra items are dropped)
| Parameter | Type | Required | What it is |
|---|---|---|---|
urls | array | Required | URLs to extract, e.g. ["https://en.wikipedia.org/wiki/Artificial_intelligence"]. Max 20 per call; extras are dropped. Failed URLs are not billed by Tavily. |
query | string | Optional | User intent for reranking extracted content chunks. When provided, chunks are reranked based on relevance to this query. |
chunks_per_source | integer | Optional | Chunks are short content snippets (about 800 characters each) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `raw_content` length. Chunks will appear in the `raw_content` field as: `<chunk 1> [...]... Default 3. Max 5. |
include_images | boolean | Optional | Include a list of images extracted from the URLs in the response. Default is false. Default false. |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
format | string | Optional | The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency. One of: markdown, text. Default "markdown". |
timeout | number | Optional | Maximum time in seconds to wait for the URL extraction before timing out. Must be between 1.0 and 60.0 seconds. If not specified, default timeouts are applied based on extract_depth: 10 seconds for basic extraction and 30 seconds for advanced extraction. Default "None". Max 60.0. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. `NOTE:`The value may be 0 if the total successful URL extractions has not yet reached 5 calls. See our Credits & Pricing documentation for details. Default false. |
Map a website: list its URLs from a root URL (no page content), with depth/breadth limits and path/domain regex filters. $0.0008 per page, billed on limit (default 50, max 500).
$0.0008 per page; set limit (default 50, max 500)
| Parameter | Type | Required | What it is |
|---|---|---|---|
url | string | Required | The root URL to begin the mapping. |
max_depth | integer | Optional | Max depth of the mapping. Defines how far from the base URL the crawler can explore. Default 1. Max 5. |
max_breadth | integer | Optional | Max number of links to follow per level of the tree (i.e., per page). Default 20. Max 500. |
limit | integer | Optional | Max pages returned (you pay per page up to this). Default 50, max 500. |
select_paths | array | Optional | Regex patterns to select only URLs with specific path patterns (e.g., `/docs/.*`, `/api/v1.*`). |
select_domains | array | Optional | Regex patterns to select crawling to specific domains or subdomains (e.g., `^docs\.example\.com$`). |
exclude_paths | array | Optional | Regex patterns to exclude URLs with specific path patterns (e.g., `/private/.*`, `/admin/.*`). |
exclude_domains | array | Optional | Regex patterns to exclude specific domains or subdomains from crawling (e.g., `^private\.example\.com$`). |
allow_external | boolean | Optional | Whether to include external domain links in the final results list. Default true. |
timeout | number | Optional | Maximum time in seconds to wait for the map operation before timing out. Must be between 10 and 150 seconds. Default 150. Max 150. |
include_usage | boolean | Optional | Whether to include credit usage information in the response.`NOTE:`The value may be 0 if the total successful pages mapped has not yet reached 10 calls. See our Credits & Pricing documentation for details. Default false. |
Live web search for agents (basic depth): ranked results with content snippets, optional LLM answer, raw page content and images. $0.008 per search.
| Parameter | Type | Required | What it is |
|---|---|---|---|
query | string | Required | The search query to execute with Tavily. |
chunks_per_source | integer | Optional | Chunks are short content snippets (about 500 characters each for `basic` and `fast`, 800 for `advanced`) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `content` length. Chunks will appear in the... Default 3. Max 3. |
max_results | integer | Optional | The maximum number of search results to return. Default 10. Max 20. |
topic | string | Optional | The category of the search.`news` is useful for retrieving real-time updates, particularly about politics, sports, and major current events covered by mainstream media sources. `general` is for broader, more general-purpose searches that may include a wide range of sources. One of: general, news, finance. Default "general". |
time_range | string | Optional | The time range back from the current date to filter results by publish date. Continuously updated pages, such as weather forecasts and prices, keep old publish dates and get filtered out. For those, leave `time_range` unset and use `max_age_hours`. By default, results with no detectable... One of: day, week, month, year, d, w, m, y. |
start_date | string | Optional | Will return all results after the specified start date based on publish date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them. |
end_date | string | Optional | Will return all results before the specified end date based on publish date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them. |
include_published_date | boolean | Optional | Include a `published_date` field in each result. The date is Tavily's best estimate of when the source was published or last updated, so it can be later than the original publish date. Results with no detectable date return `null`. Automatically enabled when `topic` is `news`. **Note**: this... Default false. |
filter_by_published_date | boolean | Optional | Remove results whose published date falls outside the `time_range`, `start_date`, or `end_date` window. Results with no detectable published date are also removed. Setting this to `true` also enables `include_published_date`. If you want date-window filtering but don't want to lose sources... Default false. |
max_age_hours | integer | Optional | The maximum age in hours of Tavily's cached copy of each result. Accepted values: - unset (default): Tavily serves cached copies and fetches pages live as needed. - `1` to `720` (30 days): only return a cached copy fetched within that many hours. - `0`: always fetch the page live. - `-1`: never... Max 720. |
include_answer | string | Optional | Include an LLM-generated answer to the provided query. `basic` or `true` returns a quick answer. `advanced` returns a more detailed answer. Default false. |
include_raw_content | string | Optional | Include the cleaned and parsed HTML content of each search result. `markdown` or `true` returns search result content in markdown format. `text` returns the plain text from the results and may increase latency. Default false. |
include_images | boolean | Optional | Include images in the response. Returns both a top-level `images` list of query-related images and an `images` array inside each result object with images extracted from that specific source. Default false. |
include_image_descriptions | boolean | Optional | When `include_images` is `true`, also add a descriptive text for each image. Default false. |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
include_domains | array | Optional | A list of domains to specifically include in the search results. Maximum 300 domains. |
exclude_domains | array | Optional | A list of domains to specifically exclude from the search results. Maximum 150 domains. |
include_domains_mode | string | Optional | Controls how `include_domains` is applied. `restrict` limits results to only the listed domains. `prefer` also searches the rest of the web, so results outside `include_domains` can still surface, rather than excluding them. Defaults to `restrict`, so `include_domains` acts as a hard filter... One of: restrict, prefer. Default "restrict". |
country | string | Optional | Boost search results from a specific country. This will prioritize content from the selected country in the search results. Available only if topic is `general`. |
language | string | Optional | Boost search results in a specific language. Accepts an ISO 639-1 code (e.g. `en`, `fr`, `zh-cn`) or an English language name (e.g. `english`, `french`). By default this only boosts matching-language results in ranking; pass `filter_by_language: true` to strictly filter out non-matching results... |
filter_by_language | boolean | Optional | Strictly filter out search results that don't match the `language` parameter, instead of only boosting them in ranking. Requires `language` to be set; returns a 400 error otherwise. Default false. |
exact_match | boolean | Optional | Ensure that only search results containing the exact quoted phrase(s) in the query are returned, bypassing synonyms or semantic variations. Wrap target phrases in quotes within your query (e.g. `"John Smith" CEO Acme Corp`). Punctuation is typically ignored inside quotes. Default false. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. Default false. |
safe_search | boolean | Optional | Whether to filter out adult or unsafe content from results. Not supported for `fast` or `ultra-fast` search depths. Default false. |
Live web search, advanced depth: highest relevance, reranked chunks per source (chunks_per_source), more latency. $0.016 per search.
| Parameter | Type | Required | What it is |
|---|---|---|---|
query | string | Required | The search query to execute with Tavily. |
chunks_per_source | integer | Optional | Chunks are short content snippets (about 500 characters each for `basic` and `fast`, 800 for `advanced`) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `content` length. Chunks will appear in the... Default 3. Max 3. |
max_results | integer | Optional | The maximum number of search results to return. Default 10. Max 20. |
topic | string | Optional | The category of the search.`news` is useful for retrieving real-time updates, particularly about politics, sports, and major current events covered by mainstream media sources. `general` is for broader, more general-purpose searches that may include a wide range of sources. One of: general, news, finance. Default "general". |
time_range | string | Optional | The time range back from the current date to filter results by publish date. Continuously updated pages, such as weather forecasts and prices, keep old publish dates and get filtered out. For those, leave `time_range` unset and use `max_age_hours`. By default, results with no detectable... One of: day, week, month, year, d, w, m, y. |
start_date | string | Optional | Will return all results after the specified start date based on publish date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them. |
end_date | string | Optional | Will return all results before the specified end date based on publish date. Required to be written in the format YYYY-MM-DD. By default, results with no detectable published date are not removed; set `filter_by_published_date` to `true` to remove them. |
include_published_date | boolean | Optional | Include a `published_date` field in each result. The date is Tavily's best estimate of when the source was published or last updated, so it can be later than the original publish date. Results with no detectable date return `null`. Automatically enabled when `topic` is `news`. **Note**: this... Default false. |
filter_by_published_date | boolean | Optional | Remove results whose published date falls outside the `time_range`, `start_date`, or `end_date` window. Results with no detectable published date are also removed. Setting this to `true` also enables `include_published_date`. If you want date-window filtering but don't want to lose sources... Default false. |
max_age_hours | integer | Optional | The maximum age in hours of Tavily's cached copy of each result. Accepted values: - unset (default): Tavily serves cached copies and fetches pages live as needed. - `1` to `720` (30 days): only return a cached copy fetched within that many hours. - `0`: always fetch the page live. - `-1`: never... Max 720. |
include_answer | string | Optional | Include an LLM-generated answer to the provided query. `basic` or `true` returns a quick answer. `advanced` returns a more detailed answer. Default false. |
include_raw_content | string | Optional | Include the cleaned and parsed HTML content of each search result. `markdown` or `true` returns search result content in markdown format. `text` returns the plain text from the results and may increase latency. Default false. |
include_images | boolean | Optional | Include images in the response. Returns both a top-level `images` list of query-related images and an `images` array inside each result object with images extracted from that specific source. Default false. |
include_image_descriptions | boolean | Optional | When `include_images` is `true`, also add a descriptive text for each image. Default false. |
include_favicon | boolean | Optional | Whether to include the favicon URL for each result. Default false. |
include_domains | array | Optional | A list of domains to specifically include in the search results. Maximum 300 domains. |
exclude_domains | array | Optional | A list of domains to specifically exclude from the search results. Maximum 150 domains. |
include_domains_mode | string | Optional | Controls how `include_domains` is applied. `restrict` limits results to only the listed domains. `prefer` also searches the rest of the web, so results outside `include_domains` can still surface, rather than excluding them. Defaults to `restrict`, so `include_domains` acts as a hard filter... One of: restrict, prefer. Default "restrict". |
country | string | Optional | Boost search results from a specific country. This will prioritize content from the selected country in the search results. Available only if topic is `general`. |
language | string | Optional | Boost search results in a specific language. Accepts an ISO 639-1 code (e.g. `en`, `fr`, `zh-cn`) or an English language name (e.g. `english`, `french`). By default this only boosts matching-language results in ranking; pass `filter_by_language: true` to strictly filter out non-matching results... |
filter_by_language | boolean | Optional | Strictly filter out search results that don't match the `language` parameter, instead of only boosting them in ranking. Requires `language` to be set; returns a 400 error otherwise. Default false. |
exact_match | boolean | Optional | Ensure that only search results containing the exact quoted phrase(s) in the query are returned, bypassing synonyms or semantic variations. Wrap target phrases in quotes within your query (e.g. `"John Smith" CEO Acme Corp`). Punctuation is typically ignored inside quotes. Default false. |
include_usage | boolean | Optional | Whether to include credit usage information in the response. Default false. |
safe_search | boolean | Optional | Whether to filter out adult or unsafe content from results. Not supported for `fast` or `ultra-fast` search depths. Default false. |