Web Reader

Reads and parses the content of the specified URL. Supports selectable return formats, cache control, image retention, and summary options.

POST /paas/v4/reader

Web Reader

cURL

curl --request POST \
  --url https://api.z.ai/api/paas/v4/reader \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "url": "https://www.example.com"
}
'

import requests

url = "https://api.z.ai/api/paas/v4/reader"

payload = { "url": "https://www.example.com" }
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({url: 'https://www.example.com'})
};

fetch('https://api.z.ai/api/paas/v4/reader', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

HttpResponse<String> response = Unirest.post("https://api.z.ai/api/paas/v4/reader")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"url\": \"https://www.example.com\"\n}")
  .asString();

200

{
  "id": "<string>",
  "created": 123,
  "request_id": "<string>",
  "model": "<string>",
  "reader_result": {
    "content": "<string>",
    "description": "<string>",
    "title": "<string>",
    "url": "<string>",
    "external": {
      "stylesheet": {}
    },
    "metadata": {
      "keywords": "<string>",
      "viewport": "<string>",
      "description": "<string>",
      "format-detection": "<string>"
    }
  }
}

{
  "code": 123,
  "message": "<string>"
}

Authorizations

Authorization · string · header · required

Use the following format for authentication: Bearer

Body

application/json

url · string · required

The URL to retrieve

timeout · integer · default: 20

Request timeout in seconds. Default is 20

no_cache · boolean · default: false

Whether to disable caching (true/false). Default is false

return_format · string · default: markdown

Return format (e.g., markdown, text). Default is markdown

retain_images · boolean · default: true

Whether to retain images (true/false). Default is true

no_gfm · boolean · default: false

Whether to disable GitHub Flavored Markdown (true/false). Default is false

keep_img_data_url · boolean · default: false

Whether to keep image data URLs (true/false). Default is false

with_images_summary · boolean · default: false

Whether to include image summary (true/false). Default is false

with_links_summary · boolean · default: false

Whether to include links summary (true/false). Default is false

Response

200

application/json

Processing successful

id · string

Task ID

created · integer<int64>

Request creation time as a Unix timestamp in seconds

request_id · string

Client-provided unique identifier to distinguish requests. If not provided, the platform will generate one.

model · string

Model code

reader_result · object

Web reading result

Hide child attributes

reader_result. content · string

Main content parsed from the page (body, images, links, etc.)

reader_result. description · string

Brief description of the page

reader_result. title · string

Page title

reader_result. url · string

Original page URL

reader_result. external · object

External resources referenced by the page

Hide child attributes

reader_result.external. stylesheet · object

Collection of external stylesheets

Hide child attributes

reader_result.external.stylesheet. {key} · object

Hide child attributes

reader_result.external.stylesheet.{key}. type · string

Stylesheet MIME type, typically text/css

reader_result. metadata · object

Page metadata

Hide child attributes

reader_result.metadata. keywords · string

Page keywords

reader_result.metadata. viewport · string

Viewport settings

reader_result.metadata. description · string

Meta description

reader_result.metadata. format-detection · string

Format detection settings, e.g., telephone=no