---
title: "Dedicated Inference: Quickstart"
sidebar_label: "Quickstart"
sidebar_position: 2
description: "How to get started with Dedicated Inference: create an inference service and connect to it"
---

import CopyIcon from '@selectel/docux/icons/copy';
import EyeIcon from '@selectel/docux/icons/eye';
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import {TabItemLabel} from '@selectel/docux/components';
import Formbricks from '@theme/MDXComponents/Formbricks';

# Dedicated Inference: Quickstart

1. [Create an inference service](#create-inference-service).
2. [Send a test request to the model](#send-request).

## 1. Create an inference service \{#create-inference-service}

1. [Select a model](#select-model).
2. [Configure the infrastructure](#configure-infrastructure).
3. [Configure the inference service](#configure-inference-service).
4. [Confirm the configuration](#confirm-configuration).

### 1. Select a model \{#select-model}

1. In the [Control panel](https://my.selectel.ru/ml/default/models-catalog/), on the top menu, click **Products** and select **Dedicated Inference**.

2. Select a [location](/infrastructure/locations.mdx). Once the inference service is created, the location cannot be changed.

3. In the model card, click **Create**.

4. Enter the name of the inference service.

5. To filter inference services in the list, add tags. A tag with the model name is added automatically. To add a new tag, in the **Tags** field, enter the tag and press **Enter**.

6. Optional: enter a description for the inference service. For example, specify its purpose.

7. Click **Continue**.

### 2. Configure infrastructure \{#configure-infrastructure}

1. Specify [model parameters](/dedicated-inference/create/model-parametrs.mdx).

   1.1. Select the data type for the KV cache.

   1.2. Select the maximum context length.

2. Select an [inference service configuration](/dedicated-inference/create/configurations.mdx). When choosing, consider the expected [model performance indicators](/dedicated-inference/create/model-performance-indicators.mdx).

   You cannot change the configuration after the inference service is created.

3. Click **Continue**.

### 3. Configure inference service \{#configure-inference-service}

1. Configure the number of inference instances.

   1.1. To have a fixed number of instances in the service, open the **Fixed** tab and specify the number of instances.

   1.2. To use autoscaling in the service, open the **With autoscaling** tab and set the minimum and maximum number of instances. The number of instances will change automatically only within the specified range depending on the load on the inference service.

   You can [change the number of inference instances](/dedicated-inference/manage/resize-inference-service.mdx#change-number-of-inference-instances) after creating the inference service. Learn more in the [Scale an inference service](/dedicated-inference/manage/resize-inference-service.mdx) instructions.

2. Select the disk type for the inference instance.

3. Select an [inference service connection type](/dedicated-inference/create/connection-types.mdx):

   * public — access via a public endpoint from the internet;

   * private — access via a private endpoint only from cloud platform devices created in the inference service subnet.

   You cannot change the connection type after the inference service is created.

4. Click **Continue**.

### 4. Confirm configuration \{#confirm-configuration}

1. Check the final inference service configuration.

2. Check the inference service price.

3. Click **Create Inference Service**. Creating an inference service may take about 15 minutes.

## 2. Send a test request to the model \{#send-request}

The request data structure depends on the model, API type, and request type. Examples of test requests to the model can be copied in the [Control Panel](https://my.selectel.ru/ml/default/inference-services/): in the top menu, click **Products** → **Inference Services** → inference service page → **Quick Start** tab → in the **Test Request** block, click <CopyIcon />.

Learn more about request types and API types in the [Inference service interaction modes](/dedicated-inference/manage/interaction-modes.mdx) instructions.

<Formbricks />