---
type: api
title: Create a Cohere inference endpoint
description: Create an inference endpoint to perform an inference task with the `cohere` service.
url: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/operation/operation-inference-put-cohere
resource: https://www.elastic.co/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/operation/operation-inference-put-cohere
products:
  - Elasticsearch
---

# Create a Cohere inference endpoint

Availability: 8.13+

## Paths

- `PUT` `/_inference/{task_type}/{cohere_inference_id}`

- [Api key auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#apikeyauth)
- [Basic auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#basicauth)
- [Bearer auth](/elastic/docs-builder/docs/4371/api/doc/elasticsearch/v8/authentication#bearerauth)

#### Path Parameters

- `task_type` (enum CohereTaskType)
  The type of the inference task that the model will perform.
  Values: `completion`, `rerank`, `text_embedding`
- `cohere_inference_id` (string Id)
  The unique identifier of the inference endpoint.

## Description

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

## Required authorization

* Cluster privileges: `manage_inference`

## Query String Parameters

- `timeout` (string Duration · default: 30s)
  Specifies the amount of time to wait for the inference endpoint to be created.

## Request Body

`application/json`

- `chunking_settings` ({} InferenceChunkingSettings) — optional
  The chunking configuration object.
  - `max_chunk_size` (number · default: 250) — optional
    The maximum size of a chunk in words.
This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).
  - `overlap` (number · default: 100) — optional
    The number of overlapping words for chunks.
It is applicable only to a `word` chunking strategy.
This value cannot be higher than half the `max_chunk_size` value.
  - `sentence_overlap` (number · default: 1) — optional
    The number of overlapping sentences for chunks.
It is applicable only for a `sentence` chunking strategy.
It can be either `1` or `0`.
  - `strategy` (string · default: sentence) — optional
    The chunking strategy: `sentence` or `word`.
- `service` (enum CohereServiceType) — required
  The type of service supported for the specified task type. In this case, `cohere`.
  Values: `cohere`
- `service_settings` ({} CohereServiceSettings) — required
  Settings used to install the inference model.
These settings are specific to the `cohere` service.
  - `api_key` (string) — required
    A valid API key for your Cohere account.
You can find or create your Cohere API keys on the Cohere API key settings page.

IMPORTANT: You need to provide the API key only once, during the inference model creation.
The get inference endpoint API does not retrieve your API key.
  - `embedding_type` (enum CohereEmbeddingType · default: float) — optional
    For a `text_embedding` task, the types of embeddings you want to get back.
Use `binary` for binary embeddings, which are encoded as bytes with signed int8 precision.
Use `bit` for binary embeddings, which are encoded as bytes with signed int8 precision (this is a synonym of `binary`).
Use `byte` for signed int8 embeddings (this is a synonym of `int8`).
Use `float` for the default float embeddings.
Use `int8` for signed int8 embeddings.
    Values: `binary`, `bit`, `byte`, `float`, `int8`
  - `model_id` (string) — optional
    For a `completion`, `rerank`, or `text_embedding` task, the name of the model to use for the inference task.

* For the available `completion` models, refer to the [Cohere command docs](https://docs.cohere.com/docs/models#command).
* For the available `rerank` models, refer to the [Cohere rerank docs](https://docs.cohere.com/reference/rerank-1).
* For the available `text_embedding` models, refer to [Cohere embed docs](https://docs.cohere.com/reference/embed).

The default value for a text embedding task is `embed-english-v2.0`.
  - `rate_limit` ({} RateLimitSetting) — optional
    This setting helps to minimize the number of rate limit errors returned from Cohere.
By default, the `cohere` service sets the number of requests allowed per minute to 10000.
    - `requests_per_minute` (number) — optional
      The number of requests allowed per minute.
  - `similarity` (enum CohereSimilarityType) — optional
    The similarity measure.
If the `embedding_type` is `float`, the default value is `dot_product`.
If the `embedding_type` is `int8` or `byte`, the default value is `cosine`.
    Values: `cosine`, `dot_product`, `l2_norm`
- `task_settings` ({} CohereTaskSettings) — optional
  Settings to configure the inference task.
These settings are specific to the task type you specified.
  - `input_type` (enum CohereInputType) — optional
    For a `text_embedding` task, the type of input passed to the model.
Valid values are:

* `classification`: Use it for embeddings passed through a text classifier.
* `clustering`: Use it for the embeddings run through a clustering algorithm.
* `ingest`: Use it for storing document embeddings in a vector database.
* `search`: Use it for storing embeddings of search queries run against a vector database to find relevant documents.

IMPORTANT: The `input_type` field is required when using embedding models `v3` and higher.
    Values: `classification`, `clustering`, `ingest`, `search`
  - `return_documents` (boolean) — optional
    For a `rerank` task, return doc text within the results.
  - `top_n` (number) — optional
    For a `rerank` task, the number of most relevant documents to return.
It defaults to the number of the documents.
If this inference endpoint is used in a `text_similarity_reranker` retriever query and `top_n` is set, it must be greater than or equal to `rank_window_size` in the query.
  - `truncate` (enum CohereTruncateType) — optional
    For a `text_embedding` task, the method to handle inputs longer than the maximum token length.
Valid values are:

* `END`: When the input exceeds the maximum input token length, the end of the input is discarded.
* `NONE`: When the input exceeds the maximum input token length, an error is returned.
* `START`: When the input exceeds the maximum input token length, the start of the input is discarded.
    Values: `END`, `NONE`, `START`

## Response

`application/json`

- `chunking_settings` ({} InferenceChunkingSettings)
  Chunking configuration object
  - `max_chunk_size` (number · default: 250)
    The maximum size of a chunk in words.
This value cannot be higher than `300` or lower than `20` (for `sentence` strategy) or `10` (for `word` strategy).
  - `overlap` (number · default: 100)
    The number of overlapping words for chunks.
It is applicable only to a `word` chunking strategy.
This value cannot be higher than half the `max_chunk_size` value.
  - `sentence_overlap` (number · default: 1)
    The number of overlapping sentences for chunks.
It is applicable only for a `sentence` chunking strategy.
It can be either `1` or `0`.
  - `strategy` (string · default: sentence)
    The chunking strategy: `sentence` or `word`.
- `service` (string)
  The service type
- `service_settings` (ServiceSettings)
  Settings specific to the service
- `task_settings` (TaskSettings)
  Task settings specific to the service and task type
- `inference_id` (string)
  The inference Id
- `task_type` (enum TaskTypeCohere)
  The task type
  Values: `text_embedding`, `rerank`, `completion`
## Code Examples

#### Console

```console
PUT _inference/text_embedding/cohere-embeddings
{
    "service": "cohere",
    "service_settings": {
        "api_key": "Cohere-Api-key",
        "model_id": "embed-english-light-v3.0",
        "embedding_type": "byte"
    }
}
```

#### JavaScript

```javascript
const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "cohere-embeddings",
  inference_config: {
    service: "cohere",
    service_settings: {
      api_key: "Cohere-Api-key",
      model_id: "embed-english-light-v3.0",
      embedding_type: "byte",
    },
  },
});
```

#### Python

```python
resp = client.inference.put(
    task_type="text_embedding",
    inference_id="cohere-embeddings",
    inference_config={
        "service": "cohere",
        "service_settings": {
            "api_key": "Cohere-Api-key",
            "model_id": "embed-english-light-v3.0",
            "embedding_type": "byte"
        }
    },
)
```

#### curl

```curl
curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/cohere-embeddings" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "cohere",
    "service_settings": {
      "api_key": "Cohere-Api-key",
      "model_id": "embed-english-light-v3.0",
      "embedding_type": "byte"
    }
  }'
```

#### Java

```java
client.inference().put(p -> p
    .inferenceId("cohere-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("cohere")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"Cohere-Api-key\",\"model_id\":\"embed-english-light-v3.0\",\"embedding_type\":\"byte\"}"))
    )
);
```

#### C#

```c#
var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "cohere-embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "cohere",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "Cohere-Api-key",
              "model_id": "embed-english-light-v3.0",
              "embedding_type": "byte"
            }
            """)
        }
    });
```

#### PHP

```php
$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "cohere-embeddings",
    "body" => [
        "service" => "cohere",
        "service_settings" => [
            "api_key" => "Cohere-Api-key",
            "model_id" => "embed-english-light-v3.0",
            "embedding_type" => "byte",
        ],
    ],
]);
```

#### Ruby

```ruby
response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "cohere-embeddings",
  body: {
    "service": "cohere",
    "service_settings": {
      "api_key": "Cohere-Api-key",
      "model_id": "embed-english-light-v3.0",
      "embedding_type": "byte"
    }
  }
)
```