API Reference

Dataset Onboarding

Overview

The Dataset Factory allows users to bring their curated geospatial datasets to the Studio to fine-tune their models. The dataset-factory endpoints allow users to onboard and delete datasets. In addition, some endpoints allow users to view their datasets' metadata. The front-end also uses the dataset-factory API to provide users with a preview of their datasets.

Where to Access

We recommend that users utilize the Geospatial Studio UI instead for the more user-friendly and appealing interface.

How to Onboard Datasets

To onboard a dataset to the Dataset Factory, the user needs to provide the following:

Field	Data Type	Example	Requirements
`dataset_name`	String (space characters allowed)	`UK 2013-2019 Flood Data`	A descriptive name which helps the user recognize the dataset would suffice
`data_sources`	List	`[{"bands": [{"index":"0", "band_name": "VV (Gray)", "description": ""},{"index":"1", "band_name": "VH", "description": ""}],"connector": "sentinelhub","collection": "s1_grd","modality_tag": "S1GRD","align_dates": "true","file_suffix": "_S1Hand.tif","scaling_factor": [1, 1]}]`	A list containing information about each data source for the dataset. Including the data connector (e.g sentinelhib or nasa_earthdata), and information about the collections (collection name, bands, scaling factor, etc)
`label_categories`	List of dictionaries	`[{ "id": "0", "name": "Floods", "description": "Flooding assets" }]`	Each dictionary in the list contains `id`, `name`, and `description`, where `id` and `label` are required fields, and `description` is not required
`dataset_url`	String	`https://ibm.box.com/shared/static/t682cwbcc5np6db9c6uj35lu2559ij26.zip`	Any link which would allow direct download of a zip file.
`description`	String (space characters allowed)	`2013-2019 Image from Sentinel Hub. The tiff files are 512 x 512 and containing 6 bands`	Something descriptive would suffice
`training_data_suffix`	List of strings (no space allowed)	`_imageHand.tif`	This is the suffix which the training image files have. This allows the onboarding pipeline to correctly find all images from all directories.
`label_suffix`	String (no space allowed)	`_labelHand.tif`	This is the suffix which all the label files have. This allows the onboarding pipeline to correctly find all labels from all directories. The `training_data_suffix` and `label_suffix` much be distinct.
`purpose`	String	`Regression`	The available options are `Regression`, `Segmentation`, `Generate`, `NER`, `Classify`, `Other`
`training_params`	Dictionary		Configure training parameters for the model

An example payload could look like the following:

{
    "dataset_name": "Sentinel Flood Multimodal",
    "data_sources": [
        {
            "bands": [
                {"index":"0", "band_name": "Coastal_aerosol", "description": ""},
                {"index":"1", "band_name": "Blue", "RGB_band": "B", "description": ""},
                {"index":"2", "band_name": "Green", "RGB_band": "G", "description": ""},
                {"index":"3", "band_name": "Red", "RGB_band": "R", "description": ""},
                {"index":"4", "band_name": "05_-_Vegetation_Red_Edge", "description": ""},
                {"index":"5", "band_name": "06_-_Vegetation_Red_Edge", "description": ""},
                {"index":"6", "band_name": "07_-_Vegetation_Red_Edge", "description": ""},
                {"index":"7", "band_name": "08_-_NIR", "description": ""},
                {"index":"8", "band_name": "08A_-_Vegetation_Red_Edge", "description": ""},
                {"index":"9", "band_name": "09_-_Water_vapour", "description": ""},
                {"index":"10", "band_name": "11_-_SWIR", "description": ""},
                {"index":"11", "band_name": "12_-_SWIR", "description": ""},
                {"index":"12", "band_name": "Cloud_Probability", "description": ""}
            ],
            "connector": "sentinelhub",
            "collection": "s2_l2a",
            "modality_tag": "S2L1C",
            "file_suffix": "_S2Hand.tif",
            "scaling_factor": [1, 1, 1, 1, 1, 1]
        },
        {
            "bands": [
                {"index":"0", "band_name": "VV (Gray)", "description": ""},
                {"index":"1", "band_name": "VH", "description": ""}
            ],
            "connector": "sentinelhub",
            "collection": "s1_grd",
            "modality_tag": "S1GRD",
            "align_dates": "true",
            "file_suffix": "_S1Hand.tif",
            "scaling_factor": [1, 1]
        }
    ],
    "label_categories": [
        {"id": "0", "name": "No Floods", "description": "Flooding assets"},
        {"id": "1", "name": "Floods", "description": "Flooding assets"}
    ],
    "dataset_url": "https://s3.us-east.cloud-object-storage.appdomain.cloud/geospatial-studio-example-data/sen1floods11_v1.1.tar.gz",
    "description": "Flood data from places",
    "label_suffix": "_LabelHand.tif",
    "purpose": "Segmentation"
}

Dataset Requirements

To successfully onboard a curated dataset, the dataset should meet the following requirements:

The dataset if contained in a .zip files, and a direct download link is available and correctly enterd in the onboarding payload
The corresponding image and label files should have the same filesname, excluding the suffixes. As an example, subsetted_512x512_HLS.S30.T10SEH.2018190.v1.4_merged.tif and subsetted_512x512_HLS.S30.T10SEH.2018190.v1.4.mask.tif are a corresponding pair, where subsetted_512x512_HLS.S30.T10SEH.2018190.v1.4 is the matching filename body, and _merged.tif and .mask.tif are the suffixes. If the names don't match, onboarding won't proceed.
For any dataset for Segmentation purpose, please make sure 2 categories are included in the label_categories field in the onboarding payload.

Dataset Factory API Endpoints

List Datasets

GET /v2/datasets

Lists all datasets available to the logged in user.

Example

Curl

curl -kX GET /v2/datasets \
-H 'Accept: application/json' \
-H 'X-API-Key: {API_KEY}'

Parameters and Responses

Success ResponseQuery Parameters

    {
    "total_records": 0,
    "page_count": 0,
    "results": [
        {
        "id": "string",
        "active": true,
        "created_by": "",
        "created_at": "2026-03-09T09:02:40.666Z",
        "updated_at": "2026-03-09T09:02:40.666Z",
        "dataset_name": "string",
        "description": "",
        "dataset_url": "",
        "label_suffix": "",
        "purpose": "",
        "data_sources": "string",
        "label_categories": "string",
        "size": "",
        "status": "",
        "error": "",
        "logs": "",
        "onboarding_options": {}
        }
    ]
    }

Name	In	Type	Required	Description
dataset_name	query	string	false	Filter by the name of the dataset.
purpose	query	array	false	Filter by the dataset purpose.
status	query	string	false	Filter by the status of the dataset.
summary	query	boolean	false	Flag to return summary of datasets or full view.
limit	query	integer	false	The maximum number of items to retrieve (default: 25).
skip	query	integer	false	The number of items to skip (default: 0).

Retrieve Dataset

GET /v2/datasets/{dataset_id}

Retrieves a single dataset by the dataset_id.

Example

Curl

curl -kX GET /v2/datasets/{dataset_id} \
-H 'Accept: application/json' \
-H 'X-API-Key: {API_KEY}'

Parameters and Responses

Success Response

{
  "id": "string",
  "dataset_name": "string",
  "description": "string",
  "purpose": "Segmentation",
  "dataset_url": "string",
  "label_suffix": "string",
  "data_sources": [],
  "label_categories": [],
  "status": "completed",
  "created_by": "string",
  "created_at": "2025-08-27T07:18:25.834Z",
  "updated_at": "2025-08-27T07:18:25.834Z"
}

Submit Dataset for Onboarding

POST /v2/datasets/onboard

Submits a new dataset for onboarding to the Dataset Factory.

Example

Curl

curl -kX POST /v2/datasets/onboard \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'X-API-Key: {API_KEY}'
-d '{
  "dataset_name": "Sentinel Flood Multimodal",
  "data_sources": [
    {
      "bands": [
        {"index":"0", "band_name": "Coastal_aerosol", "description": ""},
        {"index":"1", "band_name": "Blue", "RGB_band": "B", "description": ""},
        {"index":"2", "band_name": "Green", "RGB_band": "G", "description": ""},
        {"index":"3", "band_name": "Red", "RGB_band": "R", "description": ""}
      ],
      "connector": "sentinelhub",
      "collection": "s2_l2a",
      "modality_tag": "S2L1C",
      "file_suffix": "_S2Hand.tif",
      "scaling_factor": [1, 1, 1, 1]
    }
  ],
  "label_categories": [
    {"id": "0", "name": "No Floods", "description": "Non-flooded areas"},
    {"id": "1", "name": "Floods", "description": "Flooded areas"}
  ],
  "dataset_url": "https://s3.us-east.cloud-object-storage.appdomain.cloud/geospatial-studio-example-data/sen1floods11_v1.1.tar.gz",
  "description": "Flood detection dataset",
  "label_suffix": "_LabelHand.tif",
  "purpose": "Segmentation"
}'

Parameters and Responses

Request BodySuccess ResponseOther Responses

See the How to Onboard Datasets section above for the complete payload structure and field requirements.

{
  "dataset_id": "string",
  "status": "Pending",
  "message": "Dataset submitted for onboarding"
}

Status	Meaning	Description
201	Created	Dataset successfully submitted
422	Unprocessable Entity	Validation Error

Delete Dataset

DELETE /v2/datasets/{dataset_id}

Deletes a dataset by its ID.

Example

Curl

curl -kX DELETE /v2/datasets/{dataset_id} \
-H 'Accept: application/json' \
-H 'X-API-Key: {API_KEY}'

Parameters and Responses

Success ResponseOther Responses

{
  "message": "Dataset successfully deleted"
}

Status	Meaning	Description
200	OK	Dataset successfully deleted
422	Unprocessable Entity	Validation Error

Geospatial Studio Fine-tuning APIs

The Geospatial Tuning Studio provides users with a no-code way to create fine-tuned models for specific applications. The user will select the type of task they wish to carry out, the tuning dataset and the backbone model they wish to start from.

Workflow

The fine-tuning process involves the following key steps:

Select or create a Fine-Tuning dataset in the Dataset Factory service: choose or upload geospatial data with corresponding labels that will be used for training.
Select a tuning task type (e.g Regression or Segmentation) from a template and configure model parameters if need be or use defaults.
Specify the base-model, downstrean task and tuning parameters: configure parameters related to the foundation model and the fine-tuning process.
Submit a tuning job: Launch a tuning job that will adapt the model to your specified downstream task.
Monitor training and performance: Track the progress of the fine-tuning process by monitor training metrics.
Deploy model for inferencing: After fine-tuning, the output is a model checkpoint and configuration files. With these files, the model can be deployed to an inference service for real-world applications.

Dataset Options

To fine-tune a model for a downstream task, you need a labeled fine-tuning dataset. The Geospatial Tuning Studio provides multiple ways to acquire or upload a dataset through the dataset-factory.

Dataset Factory Docs

Fine-Tuning Components

The fine-tuning process involves four essential components:

Base Models / Foundation Models: Pre-trained models that serve as the starting point for fine-tuning. These models have been trained on large geospatial datasets and are adaptable to specific tasks.
Downstream Tasks: These are specific tasks for which the base model is fine-tuned. Examples include tasks like flooding, fire-scars, land classification and other geospatial analyses.
Datasets: A Curated set of geospatial data with corresponding labels required for fine-tuning.
Tunes: Tunes represent the fine-tuning process itself, where the model is trained on the specified dataset and task parameters. Each tune results in a fine-tuned version of the model.

API Overview

These APIs allow users to programmatically interact with the Geospatial Tuning Studio for a variety of tasks.

Tunes

Tuning geospatial models

List Tunes

GET /v2/tunes

Lists all fine tuning jobs available to the logged in user.

Example

Curl

curl -kX GET /v2/tunes \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseQuery Parameters

{
"total_records": 0,
"page_count": 0,
"results": [
    {
    "id": "string",
    "active": true,
    "created_by": "",
    "created_at": "2025-08-27T07:18:25.834Z",
    "updated_at": "2025-08-27T07:18:25.834Z",
    "name": "string",
    "description": "string",
    "task": {
        "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
        "name": "string"
    },
    "dataset_id": "string",
    "base_model": {
        "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
        "name": "string"
    },
    "mcad_id": "",
    "status": "",
    "latest_chkpt": "",
    "logs": "",
    "metrics": ""
    }
]
}

Name	In	Type	Required	Description
name	query	any	false	Filter by the name of the tune.
status	query	any	false	Filter by the status of the tune.
limit	query	any	false	The maximum number of items to retrieve.
skip	query	any	false	The number of items to skip.

Retrieve Tune

GET /v2/tunes/{tune_id}

Retrieves a single fine-tuning job by the tune_id

Example

Curl

curl -kX GET /v2/tunes/{tune_id} \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success Response

{
"id": "string",
"active": true,
"created_by": "",
"created_at": "2025-08-27T07:20:03.484Z",
"updated_at": "2025-08-27T07:20:03.484Z",
"name": "string",
"description": "string",
"task": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "name": "string"
},
"dataset_id": "string",
"base_model": {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "name": "string"
},
"mcad_id": "",
"status": "",
"latest_chkpt": "",
"logs": "string",
"metrics": [],
"config_json": {},
"progress": {
    "additionalProp1": {}
},
"logs_presigned_url": "string",
"tuning_config": "string",
"tuning_config_presigned_url": "string",
"train_options": {}
}

Submit Tune

POST /v2/submit-tune

Example

Curl

curl -kX POST /v2/submit-tune \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}' \
-d '{
"name": "string",
"description": "string",
"dataset_id": "string",
"base_model_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"tune_template_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"model_parameters": {},
"train_options": {}
}'

Parameters and Responses

Success ResponseOther Responses

{
"tune_id": "string",
"mcad_id": "string",
"status": "Pending",
"message": {
    "additionalProp1": {}
    }
}

Status	Meaning	Description	Schema
201	Created	Successful Response	TuneSubmitOut
422	Unprocessable Entity	Validation Error	HTTPValidationError

Update Tune

PATCH /v2/tunes/{tune_id}

Updates tune metadata fields.

Example

Curl

curl -kX PATCH /v2/tunes/{tune_id} \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'
-d '{
    "name": "segmentation-test-1",
    "description": "Segmentation demo example"
}

Parameters and Responses

Success ResponseQuery Parameters

{
    "message": "Tune successfully updated."
}

Status	Meaning	Description	Schema
200	OK	Successful Response	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationError

Delete Tune

DELETE /v2/tunes/{tune_id}

Example

Curl

curl -kX DELETE /v2/tunes/{tune_id} \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Status	Meaning	Description	Schema
204	No Content	Successful Response	None
422	Unprocessable Entity	Validation Error	HTTPValidationError

Try out Tuned Model

POST /v2/tunes/{tune_id}/try-out

Example

Curl

curl -kX POST /v2/tunes/{tune_id}/try-out \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}' \
-d '
{
"model_display_name": "",
"description": "try-out",
"location": "string",
"geoserver_layers": {
    "additionalProp1": {}
},
"spatial_domain": {
    "bbox": [
    [
        0
    ]
    ],
    "polygons": [
    "string"
    ],
    "tiles": [
    "string"
    ],
    "urls": [
    "string"
    ]
},
"temporal_domain": [
    "string"
],
"model_input_data_spec": [
    {
    "additionalProp1": {}
    }
],
"data_connector_config": [
    {
    "connector": "string",
    "collection": "string",
    "bands": [
        {
        "additionalProp1": {}
        }
    ],
    "scaling_factor": [
        0
    ],
    "additionalProp1": {}
    }
],
"geoserver_push": [
    {
    "workspace": "string",
    "layer_name": "string",
    "display_name": "string",
    "filepath_key": "string",
    "file_suffix": "string",
    "geoserver_style": "string",
    "additionalProp1": {}
    }
]
}'

Parameters and Responses

Success ResponseOther Responses

{
"spatial_domain": {
    "bbox": [
    [
        0
    ]
    ],
    "polygons": [
    "string"
    ],
    "tiles": [
    "string"
    ],
    "urls": [
    "string"
    ]
},
"temporal_domain": [
    "string"
],
"fine_tuning_id": "string",
"model_display_name": "string",
"description": "string",
"location": "string",
"geoserver_layers": {
    "additionalProp1": {}
},
"demo": {
    "additionalProp1": {}
},
"model_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"inference_output": {
    "additionalProp1": {}
},
"id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"active": true,
"created_by": "",
"created_at": "2025-08-27T07:24:07.317Z",
"updated_at": "2025-08-27T07:24:07.317Z",
"status": "string",
"tasks_count_total": 0,
"tasks_count_success": 0,
"tasks_count_failed": 0
}

Status	Meaning	Description	Schema
200	OK	Successful Response	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationError

Download Tunes

GET /v2/tunes/{tune_id}/download

Example

Curl

curl -kX GET /v2/tunes/{tune_id}/download \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseOther Responses

{
    "id": "string",
    "name": "string",
    "description": "string",
    "config_url": "string",
    "checkpoint_url": "string"
}

Status	Meaning	Description	Schema
200	OK	Successful Response	TuneDownloadOut
422	Unprocessable Entity	Validation Error	HTTPValidationError

Get Tune Metrics

GET /v2/tunes/{tune_id}/metrics

Example

Curl

curl -kX GET /v2/tunes/{tune_id}/metrics \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success Response

{
    "id": "string",
    "status": "FINISHED",
    "epochs": "string",
    "metrics": [
        {}
    ],
    "details": "string"
}

Other Responses

Status	Meaning	Description	Schema
200	OK	Successful Response	TunedModelMlflowMetrics
422	Unprocessable Entity	Validation Error	HTTPValidationError

Templates

Managing available tuning tasks (i.e. experiment templates)

List Templates

GET /v2/tune-templates

Example

Curl

curl -kX GET /v2/tune-templates \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseQuery ParametersOther Responses

        {
"total_records": 0,
"page_count": 0,
"results": [
    {
    "id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
    "active": true,
    "created_by": "",
    "created_at": "2025-08-27T07:26:11.139Z",
    "updated_at": "2025-08-27T07:26:11.139Z",
    "name": "string",
    "description": "string",
    "purpose": "string",
    "extra_info": {
        "additionalProp1": {}
    }
    }
]
}

Name	In	Type	Required	Description
name	query	any	false	Filter by the name of the tune.
limit	query	any	false	The maximum number of items to retrieve.
skip	query	any	false	The number of items to skip.

Status	Meaning	Description	Schema
200	OK	Successful Response	TasksOut
422	Unprocessable Entity	Validation Error	HTTPValidationError

Create Tune Template

POST /v2/tune-templates

Example

Curl

curl -kX POST /v2/tune-templates \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}' \
-d '{
    "name": "string",
    "description": "string",
    "content": "string",
    "model_params": {},
    "extra_info": {
        "runtime_image": ""
    },
    "dataset_id": "string"
}

Parameters and Responses

Success ResponseOther Responses

{
    "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08"
}

Status	Meaning	Description	Schema
201	Created	Successful Response	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationError

Retrieve Task

GET /v2/tune-templates/{task_id}

Example

Curl

curl -kX GET /v2/tune-templates/{task_id} \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseOther Responses

{
    "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
    "active": true,
    "created_by": "",
    "created_at": "2019-08-24T14:15:22Z",
    "updated_at": "2019-08-24T14:15:22Z",
    "name": "string",
    "description": "string",
    "model_params": {},
    "extra_info": {
    "additionalProp1": {}
    }
}

Status	Meaning	Description	Schema
200	OK	Successful Response	TaskOut
422	Unprocessable Entity	Validation Error	HTTPValidationError

Render Tuning Template

GET /v2/tune-templates/{task_id}/test-render

Check Task Content Rendered With Defaults

Example

Curl

curl -kX GET /v2/tune-templates/{task_id}/test-render \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseQuery ParametersOther Responses

"string"

Name	In	Type	Required	Description
task_id	path	any	true	none
dataset_id	query	any	true	none
base_model	query	any	true	none

Status	Meaning	Description	Schema
200	OK	Successful Response	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationError

Base models

Available foundation model bases

List Base Models

GET /v2/base-models

Example

Shell

# You can also use wget
curl -kX GET /v2/base-models \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseQuery ParametersOther Responses

{
    "total_records": 0,
    "page_count": 0,
    "results": [
        {
            "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
            "active": true,
            "created_by": "",
            "created_at": "2019-08-24T14:15:22Z",
            "updated_at": "2019-08-24T14:15:22Z",
            "name": "string",
            "description": "string",
            "checkpoint_filename": "string",
            "model_params": {}
            }
        ]
    }

Name	In	Type	Required	Description
name	query	any	false	Filter by the name of the tune.
limit	query	any	false	The maximum number of items to retrieve.
skip	query	any	false	The number of items to skip.

Status	Meaning	Description	Schema
200	OK	Successful Response	BaseModelsOut
422	Unprocessable Entity	Validation Error	HTTPValidationError

Create Base Model

POST /v2/base-models

Example

Shell

# You can also use wget
curl -kX POST /v2/base-models \
-H 'Content-Type: application/json' \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'
-d '
{
"name": "string",
"description": "string",
"checkpoint_filename": "",
"model_params": {
    "backbone": "",
    "patch_size": 16,
    "num_layers": 12,
    "embed_dim": 768,
    "num_heads": 12,
    "tile_size": 1,
    "tubelet_size": 1,
    "model_category": "prithvi"
}
}'

Parameters and Responses

Success ResponseOther Responses

"string"

Status	Meaning	Description	Schema
201	Created	Successful Response	Inline
422	Unprocessable Entity	Validation Error	HTTPValidationError

Retrieve Base Model

GET /v2/base-models/{base_id}

Example

Curl

# You can also use wget
curl -kX GET /v2/base-models/{base_id} \
-H 'Accept: application/json' \
-H 'Authorization: Bearer {access-token}'

Parameters and Responses

Success ResponseOther Responses

{
    "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08",
    "active": true,
    "created_by": "",
    "created_at": "2019-08-24T14:15:22Z",
    "updated_at": "2019-08-24T14:15:22Z",
    "name": "string",
    "description": "string",
    "checkpoint_filename": "string",
    "model_params": {}
}

Status	Meaning	Description	Schema
200	OK	Successful Response	BaseModelOut
422	Unprocessable Entity	Validation Error	HTTPValidationError