[role="xpack"]
[[put-inference-api]]
=== Create {infer} API

experimental[]

Creates a model to perform an {infer} task.


[discrete]
[[put-inference-api-request]]
==== {api-request-title}

`PUT /_inference/<task_type>/<model_id>`


[discrete]
[[put-inference-api-prereqs]]
==== {api-prereq-title}

* Requires the `manage` <<privileges-list-cluster,cluster privilege>>.

[discrete]
[[put-inference-api-desc]]
==== {api-description-title}

The create {infer} API enables you to create and configure an {infer} model to
perform a specific {infer} task.


[discrete]
[[put-inference-api-path-params]]
==== {api-path-parms-title}


`<model_id>`::
(Required, string)
The unique identifier of the model.

`<task_type>`::
(Required, string)
The type of the {infer} task that the model will perform. Available task types:
* `sparse_embedding`,
* `text_embedding`.


[discrete]
[[put-inference-api-request-body]]
== {api-request-body-title}

`service`::
(Required, string)
The type of service supported for the specified task type.
Available services:
* `elser`

`service_settings`::
(Required, object)
Settings used to install the {infer} model. These settings are specific to the
`service` you specified.

`task_settings`::
(Optional, object)
Settings to configure the {infer} task. These settings are specific to the
`<task_type>` you specified.


[discrete]
[[put-inference-api-example]]
==== {api-examples-title}

The following example shows how to create an {infer} model called
`my-elser-model` to perform a `sparse_embedding` task type.

[source,console]
------------------------------------------------------------
PUT _inference/sparse_embedding/my-elser-model
{
  "service": "elser",
  "service_settings": {
    "num_allocations": 1,
    "num_threads": 1
  },
  "task_settings": {}
}
------------------------------------------------------------
// TEST[skip:TBD]


Example response:

[source,console-result]
------------------------------------------------------------
{
  "model_id": "my-elser-model",
  "task_type": "sparse_embedding",
  "service": "elser",
  "service_settings": {
    "num_allocations": 1,
    "num_threads": 1
  },
  "task_settings": {}
}
------------------------------------------------------------
// NOTCONSOLE