Do you have any questions? Just write us an email or ask us through the feedback section.


The output contains information about the status of the request and about all the parts of document extracted. The information provided is the same for the different output formats and the naming convention used for all fields is snake_case.


These are the fields included in the response document

Name Description

Contains information about the extraction process and whether it has finished successfully. It is formed by a status code (code), a natural number that identifies the result, and a message (msg), a string describing the result. In addition, the field (credits) contains a natural number that indicates the credits consumed in the request and (remaining_credits) shows the number of credits left to the user to get to the credit limit.

You can find all the possible status codes returned by the API with an explanation and tips on how to manage them in our error codes catalog.

A request is any HTTP request done to the API to analyze less than 500 words. If the text sent is longer than that, then it will be considered that more than a request is made, more specifically, as many requests as we would need if the text were divided in chunks of 500 words.

For instance, an HTTP request with 1013 words, will count as three requests, so 3 credits will be consumed; an HTTP request with a text 25648 words long would count as 25648/500 = 51.296 => 52 credits, and so on.

title Title extracted from the document. The order of precedence for title selection is the following: <title>, if it doesn't exist, and the first element of the document is a heading, then the heading is considered the title. If no title or heading exists, it tries to determine if the first paragraph of the document has a title format (length, relative length and capitalization).
heading_list Takes into account all the heading tags found in the text, as well as paragraphs that follow what can be considered a title format (length, relative length and capitalization).
abstract_list It will include the pieces of text than include abstract markers such as abstract, introduction, overview or summary.

This element will contain different sections of an email:

  • from: string with the sender.
  • to: array of strings with all the contacts the email is sent to.
  • cc: array of strings with all the contacts in copy in the email.
  • subject: string with the subject of the email.

Response examples

The format in which this information will be shown will depend on the value of the of parameter.
  "status": {
    "code": "0",
    "msg": "OK",
    "credits": "8"
  "title": "Margaret Hamilton (scientist) - Wikipedia",
  "abstract_list": [ ],
  "heading_list": [
    "Margaret Hamilton (scientist)",
    "Early life[edit]",
    "SAGE Project[edit]",
    "Personal life[edit]",
    "See also[edit]",
    "External links[edit]",
    "Navigation menu",
    "Apollo 11[edit]",
    "Personal tools",
    "In other projects",
  "emails_info": {
    "from": "",
    "to": [ ],
    "cc": [ ],
    "subject": ""
<?xml version="1.0" encoding="utf-8"?>
  <status code="0" credits="8">OK</status>
  <title><![CDATA[Margaret Hamilton (scientist) - Wikipedia]]></title>
    <header><![CDATA[Margaret Hamilton (scientist)]]></header>
    <header><![CDATA[Early life[edit]]]></header>
    <header><![CDATA[SAGE Project[edit]]]></header>
    <header><![CDATA[Personal life[edit]]]></header>
    <header><![CDATA[See also[edit]]]></header>
    <header><![CDATA[External links[edit]]]></header>
    <header><![CDATA[Navigation menu]]></header>
    <header><![CDATA[Apollo 11[edit]]]></header>
    <header><![CDATA[Personal tools]]></header>
    <header><![CDATA[In other projects]]></header>