Agentic Platform
Documentation API reference Tools Skills

Tools

HTML Extract Images

html_extract_images Content

Extract main images from a webpage with URLs and copyright info.

Extract main images from a webpage (excluding logos, icons, and decorative elements) to analyze visual content, build new web pages, and ensure proper image attribution. This agent focuses on important content images and provides image URLs, titles, and copyright information, when available.

Playground

Your organization, project and token stay in this browser's local storage and are sent straight to the API — this page never sees them.

POST
item
url required The URL to extract images fro
country_code The country code to use for the real-time fetch. 2 letters lowercase.

Billing

Fixed cost per URL requested, plus whatever fetching the page costs and one model call that picks the images out of it. The model usage follows the size of the page.

These usage SKUs can be charged on a call, including SKUs from tools this one may call.

SKU Credits Description Used by
Tool call 1 per request Charged once per successful item, on top of any usage below.
  • This tool
GPT-4o (standard), input 2,500 per million tokens Tokens the model reads from the prompt you send.
  • This tool
GPT-4o (standard), output 10,000 per million tokens Tokens the model writes in its answer.
  • This tool
GPT-4o (standard), read from cache 1,250 per million tokens Tokens the model reads from a cached prompt. Cheaper than a fresh read.
  • This tool
Live page fetch 495 per 1,000 page Fetches a page from the live web as an ordinary visitor would.
Live page fetch, hard-blocked page 7,425 per 1,000 page A page that refused every gentler attempt. Charged on top of them, so a hard-blocked page costs the whole sequence.
Live page fetch, protected page 2,475 per 1,000 page A page that refused an ordinary fetch and had to be retried. Charged on top of the ordinary attempt, not instead of it.

Schemas

item is what you send, config how the tool behaves, and the response is what you get back.

Item

object
Properties
url string required

The URL to extract images fro

country_code string | null

The country code to use for the real-time fetch. 2 letters lowercase.

Default: "us"

Example
{
  "url": "string",
  "country_code": "us"
}

Response

object
Properties
images array required

The list of images extracted from the HTML page

Items: HTMLExtractImage

Example
{
  "images": [
    {
      "image_url": "string",
      "title": "string",
      "copyright": "string"
    }
  ]
}

Type Definitions

1 type

These are the available sub-object types that can be used in the properties above.

HTMLExtractImage object
#
image_url string required

Image URL. If the image is relative, make it absolute (user will provide the domain)

title string | null required

Title (if available from alt text, title attribute or nearby headings)

copyright string | null required

Copyright information (if available)

Endpoints

POST http://agents.botify.com/{organization}/{project}/html_extract_images/process
POST http://agents.botify.com/{organization}/{project}/html_extract_images/batch_process
POST http://agents.botify.com/{organization}/{project}/html_extract_images/async_process
POST http://agents.botify.com/{organization}/{project}/html_extract_images/async_batch_process

See running a long job in the background for the polling flow.

cURL

curl -X POST "http://agents.botify.com/{organization}/{project}/html_extract_images/process" \
  -H "Authorization: Bearer $BOTIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "item": {
    "url": "<url>"
  }
}'

Raw metadata