Skip to main content
POST
Create fine-tuning job

Authorizations

Authorization
string
header
required

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

Body

application/json
training_files
string[]
required

Array of IDs of uploaded files to use for training.

Example:
style_model
string
default:vaero-2

The name of the model to fine-tune for styling. Options: 'vaero-2'.

Example:

"vaero-2"

suffix
string | null

A string of up to 16 characters that will be added to your fine-tuned model name. For example, a suffix of 'custom-name' would produce a model name like 'ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1'.

Example:

"custom-name"

match_output_length
boolean
default:false

Controls whether the model preserves the original input length. When true, the model outputs text matching the length of the input -- use this if you have curated the input text to contain all desired facts. When false, the model may shorten the output to reduce AI verbosity -- use this when the input is raw AI-generated text with minimal prompt engineering or post-processing.

Response

A fine-tuning job object.

object
string

The type of the object, always 'fine_tuning.job'.

Example:

"fine_tuning.job"

id
string

The ID of the fine-tuning job.

Example:

"ftjob-abc123"

style_model
string

The model being fine-tuned.

Example:

"vaero-2"

created_at
integer

The Unix timestamp for when the job was created.

Example:

1721764800

fine_tuned_model
string | null

The name of the fine-tuned model.

Example:

null

organization_id
string

The organization ID associated with this fine-tuning job.

Example:

"org-123"

status
string

The current status of the job.

Example:

"queued"

training_files
string[]

Array of file IDs used for training.

Example: