NAVNavbar
Logo
cURL php NodeJS Python cSharp

Content Generation – Generate API


This endpoint will provide you with a text generated based on the part of the text you define and other available parameters.

Instead of ‘login’ and ‘password’ use your credentials from https://app.dataforseo.com/api-access

<?php
// You can download this file from here https://cdn.dataforseo.com/v3/examples/php/php_RestClient.zip
require('RestClient.php');
$api_url = 'https://api.dataforseo.com/';
// Instead of 'login' and 'password' use your credentials from https://app.dataforseo.com/api-access
$client = new RestClient($api_url, null, 'login', 'password');
$post_array = array();
// simple way to set a task
$post_array[] = array(
   "text" => "SEO is",
   "max_new_tokens" => 100,
   "repetition_penalty" => 1.01,
   "stop_words" => array(
      "123",
      "\n"
   ),
   "creativity_index": 1,
   "avoid_starting_words" => array(
      "SEO",
      "search engine optimization",
      "SEO is"
   )
);
try {
   // POST /v3/content_generation/generate/live
   $result = $client->post('/v3/content_generation/generate/live', $post_array);
   print_r($result);
   // do something with post result
} catch (RestClientException $e) {
   echo "n";
   print "HTTP code: {$e->getHttpCode()}n";
   print "Error code: {$e->getCode()}n";
   print "Message: {$e->getMessage()}n";
   print  $e->getTraceAsString();
   echo "n";
}
$client = null;
?>

The above command returns JSON structured like this:

{
  "version": "0.1.20221214",
  "status_code": 20000,
  "status_message": "Ok.",
  "time": "1.3633 sec.",
  "cost": 0.00215,
  "tasks_count": 1,
  "tasks_error": 0,
  "tasks": [
    {
      "id": "02171634-1535-0499-0000-e324deb2a3cc",
      "status_code": 20000,
      "status_message": "Ok.",
      "time": "1.3070 sec.",
      "cost": 0.00215,
      "result_count": 1,
      "path": [
        "v3",
        "content_generation",
        "generate",
        "live"
      ],
      "data": {
        "api": "content_generation",
        "function": "generate",
        "text": "SEO is",
        "max_new_tokens": 100,
        "repetition_penalty": 1.01,
        "stop_words": [
          "123",
          "\n"
        ],
        "creativity_index": 1,
        "avoid_starting_words": [
          "SEO",
          "search engine optimization",
          "SEO is"
        ]
      },
      "result": [
        {
          "input_tokens": 3,
          "output_tokens": 46,
          "new_tokens": 43,
          "generated_text": "SEO is a critical part of any business’s marketing strategy. It’s one of the most cost-effective ways to get your business noticed online. It’s also one of the most misunderstood.\n",
          "supplement_token": "WHdHRA"
        }
      ]
    }
  ]
}

All POST data should be sent in the JSON format (UTF-8 encoding). The task setting is done using the POST method. When setting a task, you should send all task parameters in the task array of the generic POST array. You can send up to 2000 API calls per minute.

You can specify the number of results you want to retrieve, filter and sort them.

Below you will find a detailed description of the fields you can use for setting a task.

Description of the fields for setting a task:

Field name Type Description
text string initial target text
required field
text input for content generation;
can contain from 1 to 500 tokens
learn more about tokens on our help center
max_new_tokens integer generation limit for new tokens
required field if max_tokens is not specified
the maximum number of new tokens for generated content;
maximum value: 300;
Note: the number does not include tokens specified in the text field;
learn more about this parameter on our help center
max_tokens integer generation limit for all tokens
required field if max_new_tokens is not specified
the maximum total number of tokens for generated content;
maximum value: 1024;
Note: the number includes tokens specified in the text field
learn more about this parameter on our help center
creativity_index float creativity of content generation
optional field
if you use this field, you don’t need to use top_k / top_p / temperature
the randomness of the selection of equally probable subsequent tokens;
can take values from 0 to 1
default value: 0.8
learn more about this parameter on our help center
token_repetition_penalty float token repetition
optional field
limits the repetition of the same tokens in the generated content;
can take values from 0.5 to 2;
default value: 1
top_k integer the number of initial tokens in each iteration for choosing a subsequent word
optional field
if you use creativity_index, this field will be ignored
the higher the number, the more high-probability tokens will be shortlisted for generation;
can take values from 1 to 100;
default value: 40
learn more about this parameter on our help center
top_p float excludes initial tokens with probability lower than one
optional field
if you use creativity_index, this field will be ignored
the higher the value, the less low-probability tokens may be shortlisted for generation;
can take values from 0 to 1
default value: 0.9
Note:if both top_k and top_p are used, top_k acts first;
learn more about this parameter on our help center
temperature float controls the randomness in the output
optional field
if you use creativity_index, this field will be ignored
the lower the temperature, the more likely the model will choose words with a higher probability of occurrence;
can take values from 0 to 1;
default value: 0.7
learn more about this parameter on our help center
avoid_words array words or phrases to avoid when generating a text
optional field
you can specify up to 50 terms;
example:
["term", "optimization"]
avoid_starting_words array words or phrases to avoid in the beginning of the generated text
optional field
you can specify up to 50 terms;
example:
["SEO", "search engine optimization"]
stop_words array words or phrases to end the text
optional field
you can specify up to 50 terms;
example:
["now","subscribe"]
supplement_token string token for generating subsequent results
optional field
provided in the identical filed of the response to each request;
you can use this parameter to continue the generation of text from the initial response
supplement_token values are unique for each subsequent task
tag string user-defined task identifier
optional field
the character limit is 255
you can use this parameter to identify the task and match it with the result
you will find the specified tag value in the data object of the response

As a response of the API server, you will receive JSON-encoded data containing a tasks array with the information specific to the set tasks.

Description of the fields in the results array:

Field name Type Description
version string the current version of the API
status_code integer general status code
you can find the full list of the response codes here
Note: we strongly recommend designing a necessary system for handling related exceptional or error conditions
status_message string general informational message
you can find the full list of general informational messages here
time string execution time, seconds
cost float total tasks cost, USD
tasks_count integer the number of tasks in the tasks array
tasks_error integer the number of tasks in the tasks array returned with an error
tasks array array of tasks
        id string task identifier
unique task identifier in our system in the UUID format
        status_code integer status code of the task
generated by DataForSEO; can be within the following range: 10000-60000
you can find the full list of the response codes here
        status_message string informational message of the task
you can find the full list of general informational messages here
        time string execution time, seconds
        cost float cost of the task, USD
        result_count integer number of elements in the result array
        path array URL path
        data object contains the same parameters that you specified in the POST request
        result array array of results
            input_tokens integer number of input tokens
            output_tokens integer number of output tokens
            new_tokens integer number of new tokens
            generated_text string resulting text
            supplement_token string token for generating subsequent results
you can use this parameter to continue the generation from the end of the current result;
supplement_token values are unique for each subsequent task

‌‌