# Create a Llama inference endpoint

**PUT /_inference/{task_type}/{llama_inference_id}**

Create an inference endpoint to perform an inference task with the `llama` service.

## Required authorization

* Cluster privileges: `manage_inference`



## Servers
- http://api.example.com: http://api.example.com ()


## Authentication methods
- Api key auth
- Basic auth
- Bearer auth


## Parameters

### Path parameters
- **task_type** (string)
  The type of the inference task that the model will perform.
- **llama_inference_id** (string)
  The unique identifier of the inference endpoint.

### Query parameters
- **timeout** (string)
  Specifies the amount of time to wait for the inference endpoint to be created.

### Body: application/json (object)

- **chunking_settings** (object)
  The chunking configuration object.
  Applies only to the `text_embedding` task type.
  Not applicable to the `completion` or `chat_completion` task types.
- **service** (string)
  The type of service supported for the specified task type. In this case, `llama`.
- **service_settings** (object)
  Settings used to install the inference model. These settings are specific to the `llama` service.


## Responses
### 200


#### Body: application/json (object)
- **chunking_settings** (object)
  The chunking configuration object.
  Applies only to the `sparse_embedding` and `text_embedding` task types.
  Not applicable to the `rerank`, `completion`, or `chat_completion` task types.
- **service** (string)
  The service type
- **service_settings** (object)
  Settings specific to the service
- **task_settings** (object)
  Task settings specific to the service and task type
- **inference_id** (string)
  The inference Id
- **task_type** (string)
  The task type


[Powered by Bump.sh](https://bump.sh)