[← Back to tools]
perplexity.search

Search the web with Perplexity: pay per use, no API key

Use Perplexity from Claude, Claude Code, Cursor, ChatGPT, and other agents through one Cralo balance.

Return ranked web results from the Perplexity Search API without AI synthesis.

Price and execution

Price
$0.005
Pricing model
Fixed price per successful call
Execution class
fast

Limits

No additional limits are published for this tool.

Parameters

Fields perplexity.search accepts as JSON input.

  • querystringRequired

    Natural-language web search query.

  • countrystringOptional

    Two-letter country code used to localize search results.

  • max_resultsintegerOptional

    Maximum number of ranked web results to return.

  • max_tokens_per_pageintegerOptional

    Maximum source-content tokens processed per result page. Omit when using search_context_size; the Search API accepts one extraction mode per request.

  • search_context_size"low" | "medium" | "high"Optional

    Preset extraction depth for result pages. Cannot be combined with max_tokens_per_page on the same request.

  • search_domain_filterarray of stringOptional

    Only search these domains; prefix a domain with `-` to exclude it when supported.

  • search_recency_filter"hour" | "day" | "week" | "month" | "year"Optional

    Only use web sources published within this recent time window.

Raw input JSON Schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 1000,
      "minLength": 1,
      "description": "Natural-language web search query."
    },
    "country": {
      "type": "string",
      "pattern": "^[A-Za-z]{2}
quot;,
      "description": "Two-letter country code used to localize search results."
    },
    "max_results": {
      "type": "integer",
      "default": 10,
      "maximum": 20,
      "minimum": 1,
      "description": "Maximum number of ranked web results to return."
    },
    "max_tokens_per_page": {
      "type": "integer",
      "default": 1024,
      "maximum": 8192,
      "minimum": 256,
      "description": "Maximum source-content tokens processed per result page. Omit when using search_context_size; the Search API accepts one extraction mode per request."
    },
    "search_context_size": {
      "enum": [
        "low",
        "medium",
        "high"
      ],
      "type": "string",
      "description": "Preset extraction depth for result pages. Cannot be combined with max_tokens_per_page on the same request."
    },
    "search_domain_filter": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 255,
        "minLength": 1
      },
      "maxItems": 10,
      "uniqueItems": true,
      "description": "Only search these domains; prefix a domain with `-` to exclude it when supported."
    },
    "search_recency_filter": {
      "enum": [
        "hour",
        "day",
        "week",
        "month",
        "year"
      ],
      "type": "string",
      "description": "Only use web sources published within this recent time window."
    }
  },
  "additionalProperties": false
}

Returns

Fields a successful perplexity.search call returns.

  • querystringRequired
  • resultsarray of objectRequired
    • urlstring (uri)Required
    • datestring | nullRequired
    • titlestringRequired
    • snippetstring | nullRequired
    • last_updatedstring | nullRequired
  • request_idstringRequired
  • retrieved_atstring (date-time)Required
Raw output JSON Schema
{
  "type": "object",
  "required": [
    "query",
    "results",
    "request_id",
    "retrieved_at"
  ],
  "properties": {
    "query": {
      "type": "string"
    },
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "title",
          "url",
          "snippet",
          "date",
          "last_updated"
        ],
        "properties": {
          "url": {
            "type": "string",
            "format": "uri"
          },
          "date": {
            "type": [
              "string",
              "null"
            ]
          },
          "title": {
            "type": "string"
          },
          "snippet": {
            "type": [
              "string",
              "null"
            ]
          },
          "last_updated": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "additionalProperties": false
      },
      "maxItems": 20
    },
    "request_id": {
      "type": "string"
    },
    "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 perplexity.search tool with this input: {"query":"Cralo","max_results":1}
Start with $1 freeSee pricing

Safety notes

Side Effect
read_only
Public Sources Only
Yes
Open World
Yes

How this compares to using Perplexity directly

You do not need a separate Perplexity 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]