---
title: "Create ModelTemplate"
method: POST
path: "/model_templates"
---

# Create ModelTemplate

`POST /model_templates`

## Request

- Base URL: `https://darwin.v7labs.com/ai`
- URL: `https://darwin.v7labs.com/ai/model_templates`
- Auth: API key in header `Authorization`

## Request body

- object
  - `name` string: The name of the ModelTemplate
  - `type` string: The ModelTemplate type. Wind currently supports "instance_segmentation", "object_detection", "classification" and "auto_annotation"
  - `docker_image` string: The Docker image URI of the ModelTemplate Integration
  - `devices` string, json: A list of supported devices for the ModelTemplate, among "cpu" and "gpu"
  - `load_params` string, json: List of optional parameters needed by the Model Template Integration to successfully load the model before inference
  - `infer_params` string, json: List of optional parameters needed by the Model Template Integration to successfully run inference
  - `train_params` string, json: List of optional parameters needed by the Model Template Integration to successfully start a TrainingSession

## Response `200`

200

- object
  - `name` string
  - `type` string
  - `docker_image` string
  - `devices` string[]
  - `train_params` object
    - `config_file` string

## Other responses

- `400`: 400

---

[API](https://skmtc.dev/v7labs/apis/wind.md) - [All operations](https://skmtc.dev/v7labs/apis/wind/llms.txt) - [OpenAPI document](https://skmtc.dev/v7labs/apis/wind/revisions/4035e136c087?raw)