Find similar pages with Exa: pay per use, no API key
Use Exa from Claude, Claude Code, Cursor, ChatGPT, and other agents through one Cralo balance.
Find pages semantically similar to a known URL using Exa, with titles, publication details, and highlights. Price covers 10 results; extra results cost more (quoted from `num_results`, max 100).
Price and execution
- Price
- $0.007
- Pricing model
- Fixed price per successful call
- Execution class
- fast
Limits
No additional limits are published for this tool.
Parameters
Fields exa.find-similar accepts as JSON input.
urlstring (uri)RequiredThe page Exa should find similar content for.
num_resultsintegerOptionalThe maximum number of similar pages to return.
exclude_source_domainbooleanOptionalExclude results from the source URL's own domain.
Raw input JSON Schema
{
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"format": "uri",
"pattern": "^https?://",
"maxLength": 2048,
"description": "The page Exa should find similar content for."
},
"num_results": {
"type": "integer",
"default": 10,
"maximum": 100,
"minimum": 1,
"description": "The maximum number of similar pages to return."
},
"exclude_source_domain": {
"type": "boolean",
"default": false,
"description": "Exclude results from the source URL's own domain."
}
},
"additionalProperties": false
}Returns
Fields a successful exa.find-similar call returns.
resultsarray of objectRequiredurlstring (uri)RequiredtitlestringRequiredauthorstring | nullRequiredhighlightsarray of stringRequiredpublished_datestring | nullRequired
cost_usdnumber | nullRequiredrequest_idstringRequiredsource_urlstring (uri)Requiredretrieved_atstring (date-time)Required
Raw output JSON Schema
{
"type": "object",
"required": [
"source_url",
"results",
"request_id",
"cost_usd",
"retrieved_at"
],
"properties": {
"results": {
"type": "array",
"items": {
"type": "object",
"required": [
"title",
"url",
"published_date",
"author",
"highlights"
],
"properties": {
"url": {
"type": "string",
"format": "uri"
},
"title": {
"type": "string"
},
"author": {
"type": [
"string",
"null"
]
},
"highlights": {
"type": "array",
"items": {
"type": "string"
}
},
"published_date": {
"type": [
"string",
"null"
],
"format": "date-time"
}
},
"additionalProperties": false
},
"maxItems": 100
},
"cost_usd": {
"type": [
"number",
"null"
],
"minimum": 0
},
"request_id": {
"type": "string"
},
"source_url": {
"type": "string",
"format": "uri"
},
"retrieved_at": {
"type": "string",
"format": "date-time"
}
},
"additionalProperties": false
}Run this tool
Copy this instruction to your agent to set up Cralo and call this tool with the example input.
Set up Cralo by following https://cralo.ai/SKILL.md, then call the exa.find-similar tool with this input: {"url":"https://example.com","num_results":1,"exclude_source_domain":true}Safety notes
- Side Effect
- read_only
- Public Sources Only
- Yes
How this compares to using Exa directly
You do not need a separate Exa account or subscription for this call. Cralo uses one prepaid balance across all tools and shows the per-call price before you run the command.
Related tools
[Browse all tools]- $0.007Exa SearchSearch the web using Exa. Returns relevant pages with titles, URLs, publication details, and highlighted passages. Price covers 10 results; extra results cost more (quoted from `num_results`, max 100).Exa
exa.searchInstant - $0.005Answer from the web with ExaAnswer a question using current web sources and return the supporting citations from Exa.Exa
exa.answerInstant - $0.001Extract content with ExaExtract clean text, relevant highlights, or summaries from known web pages using Exa. Price is per URL.Exa
exa.contentsInstant - BR$0.005Search the web with BraveSearch Brave's independent web index and return normalized web, news, video, and infobox results.Brave Search
brave.web-searchInstant - $0.002Search the web with FirecrawlSearch the public web with Firecrawl and return normalized results with optional page content.Firecrawl
firecrawl.searchInstant