POST
/
style
/
transform
curl --request POST \
  --url https://vaeroapi.com/v1/style/transform \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '{
  "mode": "full",
  "messages": [
    {
      "role": "user",
      "content": "Write a blog post about Florence."
    }
  ],
  "model": "ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1",
  "full_mode_options": {
    "base_model": "claude-3-7-sonnet-latest",
    "base_temperature": 0
  },
  "stream": false,
  "humanize": 4,
  "temperature": 0,
  "include_quality": false,
  "include_rouge": false,
  "include_compare_original": false,
  "include_distance": false,
  "skip_headings": false
}'
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The lazy dog was vaulted by a brown fox with the zoomies."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  },
  "quality_analytics": {
    "sentence_length_stats": {
      "personalized_mean": 30.0625,
      "personalized_median": 30,
      "personalized_std_dev": 11.171776660406348,
      "unpersonalized_mean": 22.96,
      "unpersonalized_median": 22,
      "unpersonalized_std_dev": 5.895625496925666,
      "ground_truth_mean": 33.471471471471475,
      "ground_truth_median": 31,
      "ground_truth_std_dev": 18.186882625578622
    },
    "lexical_diversity": {
      "mattr": {
        "unpersonalized": 0.6798949579831932,
        "personalized": 0.7728198433420366,
        "ground_truth": 0.7097187431813222
      },
      "mtld": {
        "unpersonalized": 70.3392094017094,
        "personalized": 122.59154535274357,
        "ground_truth": 85.00872715620727
      },
      "hdd": {
        "unpersonalized": 0.7704132322467299,
        "personalized": 0.84289309374695,
        "ground_truth": 0.8476210196780126
      }
    },
    "readability": {
      "flesch_reading_ease": {
        "unpersonalized": 31.21,
        "personalized": 32.46,
        "ground_truth": 37.07
      },
      "flesch_kincaid_grade": {
        "unpersonalized": 14.6,
        "personalized": 16.2,
        "ground_truth": 16.5
      }
    }
  }
}

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
mode
enum<string>
required

Use 'full' for end-to-end inference of a prompt.

Available options:
full
Example:

"full"

​
messages
object[]
required

Conversation history. Required when mode is 'full'.

Example:
[
  {
    "role": "user",
    "content": "Write a blog post about Florence."
  }
]
​
model
string
required

ID of the fine-tuned model to use.

Example:

"ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1"

​
full_mode_options
object

Options specific to 'full' mode.

​
stream
boolean
default:false

Whether to stream the response.

Example:

false

​
humanize
integer
default:0

Level of humanization to apply. 0 is none, 1 is low, and 4 is highest.

Required range: 0 <= x <= 4
Example:

4

​
temperature
number | null
default:0

Sampling temperature, between 0 and 2. Higher values make output more random. 0 is recommended for most use cases.

Example:

0

​
include_quality
boolean
default:false

Whether to include quality metrics in the response.

Example:

false

​
include_rouge
boolean
default:false

Whether to include rouge score in quality metrics. Only applies when include_quality is true.

Example:

false

​
include_compare_original
boolean
default:false

Whether to include original text for comparison to styled text.

Example:

false

​
include_distance
boolean
default:false

Whether to include distance metrics comparing the original and styled text.

Example:

false

​
skip_headings
boolean
default:false

When set to true, headings are not rewritten.

Example:

false

Response

A chat completion object.

​
id
string

ID of the chat completion.

Example:

"chatcmpl-123"

​
object
string

Type of the object, always 'chat.completion'.

Example:

"chat.completion"

​
created
integer

Unix timestamp for when the completion was created.

Example:

1677652288

​
model
string

Model used for the completion.

Example:

"ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1"

​
choices
object[]
​
usage
object
​
quality_analytics
object