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

# Create an Google AI Studio inference endpoint

Availability: 8.15+

## Paths

- `PUT` `/_inference/{task_type}/{googleaistudio_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 GoogleAiStudioTaskType)
  The type of the inference task that the model will perform.
  Values: `completion`, `text_embedding`
- `googleaistudio_inference_id` (string Id)
  The unique identifier of the inference endpoint.

## Description

Create an inference endpoint to perform an inference task with the `googleaistudio` 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 GoogleAiServiceType) — required
  The type of service supported for the specified task type. In this case, `googleaistudio`.
  Values: `googleaistudio`
- `service_settings` ({} GoogleAiStudioServiceSettings) — required
  Settings used to install the inference model. These settings are specific to the `googleaistudio` service.
  - `api_key` (string) — required
    A valid API key of your Google Gemini account.
  - `model_id` (string) — required
    The name of the model to use for the inference task.
Refer to the Google documentation for the list of supported models.
  - `rate_limit` ({} RateLimitSetting) — optional
    This setting helps to minimize the number of rate limit errors returned from Google AI Studio.
By default, the `googleaistudio` service sets the number of requests allowed per minute to 360.
    - `requests_per_minute` (number) — optional
      The number of requests allowed per minute.

## 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 TaskTypeGoogleAIStudio)
  The task type
  Values: `text_embedding`, `completion`
## Code Examples

#### Console

```console
PUT _inference/completion/google_ai_studio_completion
{
    "service": "googleaistudio",
    "service_settings": {
        "api_key": "api-key",
        "model_id": "model-id"
    }
}
```

#### JavaScript

```javascript
const response = await client.inference.put({
  task_type: "completion",
  inference_id: "google_ai_studio_completion",
  inference_config: {
    service: "googleaistudio",
    service_settings: {
      api_key: "api-key",
      model_id: "model-id",
    },
  },
});
```

#### Python

```python
resp = client.inference.put(
    task_type="completion",
    inference_id="google_ai_studio_completion",
    inference_config={
        "service": "googleaistudio",
        "service_settings": {
            "api_key": "api-key",
            "model_id": "model-id"
        }
    },
)
```

#### curl

```curl
curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/google_ai_studio_completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "googleaistudio",
    "service_settings": {
      "api_key": "api-key",
      "model_id": "model-id"
    }
  }'
```

#### Java

```java
client.inference().put(p -> p
    .inferenceId("google_ai_studio_completion")
    .taskType(TaskType.Completion)
    .inferenceConfig(i -> i
        .service("googleaistudio")
        .serviceSettings(JsonData.fromJson("{\"api_key\":\"api-key\",\"model_id\":\"model-id\"}"))
    )
);
```

#### C#

```c#
var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "google_ai_studio_completion",
        TaskType = TaskType.Completion,
        InferenceConfig = new()
        {
            Service = "googleaistudio",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "api-key",
              "model_id": "model-id"
            }
            """)
        }
    });
```

#### PHP

```php
$resp = $client->inference()->put([
    "task_type" => "completion",
    "inference_id" => "google_ai_studio_completion",
    "body" => [
        "service" => "googleaistudio",
        "service_settings" => [
            "api_key" => "api-key",
            "model_id" => "model-id",
        ],
    ],
]);
```

#### Ruby

```ruby
response = client.inference.put(
  task_type: "completion",
  inference_id: "google_ai_studio_completion",
  body: {
    "service": "googleaistudio",
    "service_settings": {
      "api_key": "api-key",
      "model_id": "model-id"
    }
  }
)
```