Web search with model-ready summaries (DeepSeek)

Liveby DeepSeek

Searches DeepSeek's own web index and returns up to 50 ranked results, each with title, URL, site, publication date, a short snippet and a 600 to 800 character summary written for a model to read, plus DeepSeek's relevance score (0 to 3; 1.5 or more is a strong match) and an authority tier for the site.

Set include_content for each page's text at no extra cost. Filter by site, language and publication date. Works well in Chinese and English. Query and filters together are limited to 128 characters.

Guide: Web search API for AI agents

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Search the web for the best-rated coworking spaces in Lisbon.

Find recent articles comparing electric scooters.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call, input and output

Web search results API by DeepSeek, callable through Superpowers. It costs $0.001 per call, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "deepseek.search", or over MCP with run_tool. 5 other providers in this category take the same input and can be compared side by side.

Tool id
Price per call: $0.001 / call

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"deepseek.search","input":{"query":"agência de marketing"},"idempotency_key":"example-request-1"}'

Input

8 fields · 1 required

{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128,
      "description": "What to search for, up to 128 characters including any filters, e.g. \"who designed the Sydney Opera House\". Supports site:, -site:, \"exact phrase\", lang:, after: and before: inside the query."
    },
    "question": {
      "type": "string",
      "maxLength": 128,
      "description": "The original question behind the search, when the query is a shortened form of it; helps ranking"
    },
    "max_results": {
      "type": "integer",
      "minimum": 1,
      "maximum": 50,
      "default": 10,
      "description": "How many results to return; the price is the same for any number"
    },
    "include_content": {
      "type": "boolean",
      "default": false,
      "description": "Also return each page's text (up to 6,000 characters per page), at no extra cost"
    },
    "sites": {
      "type": "array",
      "maxItems": 5,
      "items": {
        "type": "string"
      },
      "description": "Only these sites, e.g. [\"github.com\",\"huggingface.co\"]"
    },
    "language": {
      "type": "string",
      "pattern": "^[a-z]{2}$",
      "description": "Only pages in this language, e.g. en, pt, zh"
    },
    "after": {
      "type": "string",
      "description": "Only pages published after this date (YYYY or YYYY-MM-DD)"
    },
    "before": {
      "type": "string",
      "description": "Only pages published before this date (YYYY or YYYY-MM-DD)"
    }
  }
}

Normalized output

Example for this type of tool

The shape tools of this type share in normalized. Agents read it from GET /v1/tools/deepseek.search or MCP inspect_tool.

{
  "type": "object",
  "properties": {
    "results": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "position": {
            "type": "integer"
          },
          "title": {
            "type": "string"
          },
          "url": {
            "type": "string"
          },
          "snippet": {
            "type": "string"
          }
        },
        "required": [
          "position",
          "title",
          "url",
          "snippet"
        ]
      }
    }
  },
  "required": [
    "results"
  ]
}