Hydrafetch

Turn a URL into clean, LLM-ready markdown and structured data.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to scrape."
    },
    "formats": {
      "description": "Which outputs to return. Defaults to markdown.",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "markdown",
          "html",
          "rawHtml",
          "links",
          "structured"
        ]
      }
    },
    "preferStructure": {
      "description": "Keep headings, lists and tables as markdown. Default false optimises for raw content and can return unstructured text on marketing and listing pages. Turn on when the document structure matters, or retry with it if `structure` came back 'plain'.",
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Enumerate a site's URLs from its sitemap and links, without scraping them.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The seed URL to map."
    },
    "limit": {
      "description": "Max URLs to return.",
      "type": "integer",
      "minimum": 1,
      "maximum": 5000
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Discover and scrape a whole site as one job. Returns a crawl id straight away; read it with crawl_status. Use this instead of calling scrape in a loop.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The site to start from."
    },
    "limit": {
      "description": "Maximum pages to scrape.",
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "maxDepth": {
      "description": "How far from the seed to follow.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Read a crawl started with crawl: how far it has got, and the pages it has scraped.

{
  "type": "object",
  "properties": {
    "crawlId": {
      "type": "string",
      "description": "The id returned by crawl."
    }
  },
  "required": [
    "crawlId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Scrape a list of URLs you already have as one job. Returns a batch id straight away; read it with batch_status.

{
  "type": "object",
  "properties": {
    "urls": {
      "minItems": 1,
      "maxItems": 25000,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The URLs to scrape."
    }
  },
  "required": [
    "urls"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Read a batch started with batch: how far it has got, and the results so far.

{
  "type": "object",
  "properties": {
    "batchId": {
      "type": "string",
      "description": "The id returned by batch."
    }
  },
  "required": [
    "batchId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Search the web and return ranked results: title, url and snippet. Set scrapeResults to also fetch each result as markdown, at 1 extra credit per page.

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "The search query."
    },
    "limit": {
      "description": "Max results (default 5).",
      "type": "integer",
      "minimum": 1,
      "maximum": 15
    },
    "scrapeResults": {
      "description": "Also scrape each result to markdown, 1 extra credit per page (default false).",
      "type": "boolean"
    },
    "preferStructure": {
      "description": "Keep headings, lists and tables in each scraped result.",
      "type": "boolean"
    }
  },
  "required": [
    "query"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

A company's brand from its domain: logos for light and dark backgrounds, its real colours, name, description and socials. Answers 'what is this company' far better than a raw page dump.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "The company domain, e.g. stripe.com. A full URL works too."
    }
  },
  "required": [
    "domain"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

A company's logo as a directly embeddable image URL, chosen for the background you name. Use this rather than brand when the mark is all you need — it costs a fifth as much and returns one asset instead of the whole record.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "The company domain, e.g. stripe.com. A full URL works too."
    },
    "theme": {
      "description": "The background the logo will sit on. Defaults to light.",
      "type": "string",
      "enum": [
        "light",
        "dark",
        "auto"
      ]
    },
    "type": {
      "description": "The square mark, or the full logotype. Defaults to icon.",
      "type": "string",
      "enum": [
        "icon",
        "wordmark"
      ]
    }
  },
  "required": [
    "domain"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Pull typed structured data from one or more URLs by JSON schema or prompt.

{
  "type": "object",
  "properties": {
    "urls": {
      "minItems": 1,
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "The URLs to extract from."
    },
    "prompt": {
      "description": "Natural-language description of what to pull.",
      "type": "string"
    },
    "schema": {
      "description": "A JSON schema the result must conform to.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "preferStructure": {
      "description": "Keep headings, lists and tables in the text handed to the model.",
      "type": "boolean"
    },
    "showConfidence": {
      "description": "For each field, return a confidence score and the exact source passage the value was drawn from.",
      "type": "boolean"
    },
    "showSources": {
      "description": "Return the list of URLs that were actually extracted.",
      "type": "boolean"
    }
  },
  "required": [
    "urls"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

A site's design system read from computed styles in a real browser: colours by role with contrast ratios, the type scale, corner radius and button styling. Values defined through CSS variables come back resolved to the hex actually painted.

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "The domain to read, e.g. stripe.com. A full URL works too."
    }
  },
  "required": [
    "domain"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The URL to capture."
    },
    "fullPage": {
      "description": "Capture the whole scrollable page rather than the viewport.",
      "type": "boolean"
    },
    "viewport": {
      "description": "Screen size to render at. Defaults to desktop (1920x1080). Ignored when width or height are given.",
      "type": "string",
      "enum": [
        "desktop",
        "laptop",
        "tablet",
        "mobile"
      ]
    },
    "viewportWidth": {
      "description": "Exact viewport width in pixels. Overrides viewport.",
      "type": "integer",
      "minimum": 320,
      "maximum": 3840
    },
    "viewportHeight": {
      "description": "Exact viewport height in pixels. Overrides viewport. With fullPage the capture still extends to the full page height.",
      "type": "integer",
      "minimum": 240,
      "maximum": 2160
    },
    "waitFor": {
      "description": "Extra milliseconds to let the page settle before capture.",
      "type": "integer",
      "minimum": 0,
      "maximum": 30000
    },
    "timeout": {
      "description": "Overall time budget for the capture, in milliseconds.",
      "type": "integer",
      "minimum": 1000,
      "maximum": 120000
    },
    "maxAge": {
      "description": "Reuse a stored screenshot younger than this many milliseconds. Defaults to 7 days, so a repeat returns the stored PNG without re-rendering and without applying waitFor. Pass 0 to force a fresh capture.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Harvest a page's images with their metadata, without rendering it. Cheaper than a screenshot and returns the source images rather than a picture of the page.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "The page to harvest images from."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}