# Create Model

Create new model. A dataset can be used to train multiple models with different training versions (e.g., one light and one max). The model will belong to the same project as its dataset.

Endpoint: POST /tailored-gen/models

## Header parameters:

  - `api_token` (string, required)

## Request fields (application/json):

  - `name` (string)
    Name of the model (required)

  - `dataset_id` (integer)
    ID of the dataset to use (required)

  - `training_mode` (string)
    Defines the training configuration strategy.
* : Get good results without the guesswork. Automatically configures the training recipe based on dataset size and IP medium/type.
* : Designed for experienced users needing control over training parameters and support for larger datasets.
    Enum: "fully_automated", "expert"

  - `training_version` (string)
    Defines the foundational model used for fine-tuning.
* : supports  and  (default).  is best for complex IPs requiring high fidelity, while  is for fast generation.
* : supports  and  (default).
    Enum: "light", "max", "bria-2.3", "bria-3.2"

  - `description` (string)
    Description of the model (optional)

## Response 201 fields (application/json):

  - `id` (integer)
    Unique identifier for the model

  - `name` (string)
    Name of the model

  - `description` (string)
    Description of the model

  - `status` (string)
    Status of the model
    Enum: "Created"

  - `training_version` (string)
    Training version
    Enum: "light", "max", "bria-2.3", "bria-3.2"

  - `training_mode` (string)
    Training configuration strategy
    Enum: "fully_automated", "expert"

  - `generation_prefix` (string)
    Text drawn from the dataset's caption_prefix that is automatically prepended to generation prompts to maintain consistency. It matches the dataset's caption_prefix. It can be bypassed during generation by setting include_generation_prefix=false. This field is empty upon model creation, and filled after the training starts.

  - `project_id` (integer)
    ID of the project this model belongs to

  - `dataset_id` (integer)
    ID of the dataset used for training

  - `created_at` (string)
    Timestamp when the model was created

  - `updated_at` (string)
    Timestamp when the model was last updated.

  - `custom_metadata` (string)
    Custom metadata associated with the model.

  - `active_model_version` (string)
    The active version (checkpoint) of the model. becomes relevant after a training has been completed.

  - `training_parameters` (object)
    The training parameters used for the model. will be filled using the /start_training endpoint.

  - `checkpoint_steps` (array)
    A list of checkpoints saved for the model. will be filled using the /start_training endpoint.

## Response 400 fields (application/json):

  - `error_code` (string)

  - `message` (string)