How-to Guides

Create Simple AI Inference

To use Simple AI Inference, you must first create an Inference. To create an inference, follow these steps.

1. Click the All Services > AI-ML > Simple AI Inference menu. 1. Navigate to the Service Home page of Simple AI Inference.

2. On the Service Home page, click the Simple AI Inference Create button. 2. Go to the Serverless Inference creation page.

3. Serverless Inference Creation page: enter the information required to create the service and select detailed options.

   • In the Service Information Input area, select the options required to create the service.

     Category	Required	Detailed description
     Inference service name	Required	Serverless Inference Enter service name Enter using lowercase English letters and numbers, 3 ~ 25 characters
     Endpoint	Required	Select external access for Simple AI Inference Private: Use only private endpoint access control Private&Public: Use both private and public endpoint access control
     Private endpoint access control	Selection	Add resources within the Samsung Cloud Platform and allow access only to those resources Private Access Allowed Resources: Select the resources to grant access to Click the Add button to select resources to grant access to Select the resource to delete from the resource list, then click the Delete button to remove it If no resources are added, access is allowed to all resources on subnets within the same region Can be modified after applying for a Serverless endpoint
     Public endpoint access control	Selection	Set whether to use public endpoint access control Use if set, you can add IPs or resources that are allowed to access Public Access Allowed IP: After entering the IP range to allow access in CIDR format or as an IP address, you can add it by clicking the Add button You can add up to 100 entries If not used, access is allowed for all IPs Can be modified after applying for a Serverless endpoint

     Table. Serverless Inference service information input items

     Caution

     If you do not use public endpoint access control or set it to the entire IP range (Any, 0.0.0.0/0), the registry may be exposed to security attacks such as external scanning and hacking.
   • Additional Information Input area, enter or select the required information.

     Category	Required	Detailed description
     tag	Selection	Add Tag You can add up to 50 per resource After clicking the Add Tag button, enter or select Key, Value values

     Table. Serverless Inference additional information entry fields

4. Summary Check the detailed information and estimated charges generated in the panel, and click the Create button.

5. When the popup indicating creation opens, click the Confirm button. 5. The creation request is complete.

   • When creation is complete, check the created items on the Serverless Inference List page.

Checking usage per LLM model

In the Service Home page of Simple AI Inference, you can view the list of LLMs and token usage per model.

1. Click the All Services > AI-ML > Simple AI Inference menu. 1. Navigate to the Service Home page of Simple AI Inference.
2. On the dashboard of the Service Home page, check the LLM usage by model in the LLM model usage list.

   Category	Detailed description
   Model name	LLM name Click the name to go to the Report tab on the model’s detail page
   model type	LLM type For model-specific information, see Provided Model
   Token usage (1 Week)	Token usage for the past week as of today

   Table. Simple AI Inference LLM model usage items

Check detailed information of Serverless Inference

To view detailed information about Serverless Inference, follow the steps below.

1. All Services > AI-ML > Simple AI Inference Click the menu. 1. Navigate to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the Serverless Inference menu. 2. Navigate to the Serverless Inference List page.

   Item	Explanation
   Create Service	Serverless Inference can be created When the button is clicked, navigate to the Serverless Inference creation page Refer to Simple AI Inference Creation for creation method
   Inference service name	Serverless Inference name
   Model ID	Model ID value When the model ID is clicked, navigate to the detailed page of that model For detailed information about the model, see 모델 상세 정보 확인하기
   Model name	Model Name When the Model ID is clicked, navigate to the detailed page of that model For detailed information about the model, see View model details
   Planned model termination date	Model’s scheduled end-of-service date
   Latency	Average response time
   throughput	The average number of tokens the model generates per second
   Service termination	Serverless Inference can be terminated When the button is clicked, navigate to the Serverless Inference termination page Refer to Inference termination for termination instructions

   Table. Serverless Inference list information

   Reference

   Clicking Model ID or Model name takes you to the model detail page in the Model Catalog, where you can view the model’s detailed information.

3. Serverless Inference List On the page, click the Inference service name to view detailed information. 3. Serverless Inference Details Navigate to the page.
   • Serverless Inference Details page consists of Details, Report, Tags, Job History tabs.

Detailed information

On the Serverless Inference List page, you can view detailed information of the selected resource and edit the information if needed.

Report

On the Serverless Inference list page, you can view the daily LLM call count and token usage for the selected resource.

Tag

Serverless Inference List page lets you view the tag information of selected resources, and you can add, modify, or delete them.

Job History

You can view the operation history of the selected resource on the Serverless Inference list page.

Check model detailed information

You can view the models provided by Simple AI Inference and their detailed information. To view the detailed model information, follow these steps.

1. All Services > AI-ML > Simple AI Inference Click the menu. 1. Go to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the Model Catalog menu. 2. Go to the Model Catalog page.
3. On the Model Catalog page, click the model whose detailed information you want to view. 3. Model Catalog Navigate to the detail page.

   Item	Explanation
   License	Click the button to view the model’s license information.
   Overview	Basic description of the model
   Sales criteria	Model developer
   Category	Model usage scope
   Latest version	Provided version
   Release date	Model release year and date
   Model ID	Model ID information
   Maximum token	Maximum token size
   Output modelities	Model output method
   Input modelities	Model input method
   language	Model language types
   Deployment type	Model deployment method
   Token Limits	Token limit value
   Reqeust Limits	request limit

   Table. Detailed information on the model provided by Simple AI Inference

Managing API Keys

You need to create and register an API key to use Simple AI Inference in Severless Inference.

Create API Key

To create an API key, follow these steps.

1. Click the All Services > AI-ML > Simple AI Inference menu. 1. Go to the Service Home page of Simple AI Inference.

2. On the Service Home page, click the API Key menu. 2. Go to the API key list page.

3. On the API Key List page, click the Create Key button. 3. API Key Creation Navigate to the detail page.

4. On the Create API Key page, after entering the information required to generate an API key, click the Create button.

   Category	Required	Detailed description
   Inference type	Required	Select inference type
   Expiration period	required	Enter the expiration period of the API key permanent If you check the item, it can be used without a time limit
   Intended use	Selection	Enter the usage purpose of the API key within 128 characters

   Table. Serverless Inference Service Information Input Items

   Caution

   If you do not use public endpoint access control or set it to the entire IP range (Any, 0.0.0.0/0), the registry can be exposed to security attacks such as external scanning and hacking.

5. When the popup notifying the creation of an API key opens, click the Confirm button.

   • When an API key is created, it is downloaded once at the time of creation.

Check API Key

To check the API key, follow these steps.

1. Click the All Services > AI-ML > Simple AI Inference menu. 1. Go to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the API Key menu. 2. Go to the API key list page.

   Item	Explanation
   authentication key	Authentication key information
   Inference type	Inference type with a registered authentication key
   Creation Date/Time	Authentication key creation time
   Expiration date and time	Authentication key expiration time
   Delete	Delete the selected API key API keys can only be deleted when deactivated Deleted API keys cannot be recovered See Delete API key for how to delete an API key
   More	Change the activation/deactivation status of the selected API key Enable: Activate a disabled authentication key Disable: Deactivate an active authentication key Refer to API 키 상태 변경하기 for how to change the API key status
   Key generation	Create API key When the button is clicked, navigate to the Create API Key page Refer to API 키 생성하기 for how to create an API key

   Table. Detailed information on the Simple AI Inference provided model

Change API Key Status

You can enable or disable an API key’s status. To change the status of an API key, follow these steps.

1. All Services > AI-ML > Simple AI Inference menu, please click. 1. Go to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the API Key menu. 2. API key list go to the page.
3. On the API Key List page, select all API keys whose status you want to change.
4. After clicking the More button at the top of the list, click the Use or Disable button.
   • If the API key is active: click the Use button to activate
   • If the API key is disabled, you can click the Disable button to deactivate it.
5. When a popup that notifies a status change opens, click the Confirm button.

Delete API Key

To delete an API key, follow these steps.

1. All Services > AI-ML > Simple AI Inference Click the menu. 1. Navigate to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the API Key menu. 2. API Key List go to the page.
3. On the API Key List page, verify that the API key you are deleting is disabled.
   • If the API key is active, refer to API 키 상태 변경하기 and change it to inactive.
4. On the API key list page, select all API keys you want to delete, then click the Delete button.
5. When the deletion notification popup opens, click the Confirm button.

Using PlayGround

Using PlayGround, you can directly test AI models in a web browser without any coding, compare performance, input prompts, adjust parameters, extract API code, and perform these tasks in real time, allowing you to quickly validate ideas. To use PlayGround, follow these steps.

1. All Services > AI-ML > Simple AI Inference menu, please click. 1. Navigate to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the PlayGround menu. 2. Navigate to the PlayGround page.

   Item	Explanation
   Model information area	Display the currently set model name Click the dropdown button to change the model When changing the model, all conversation content will be reset
   Parameter setting	Set Playground parameter values System Prompt(required): Specific instructions to give the model (e.g., a particular persona, tone, behavior rules, etc.) Maximum Generation Tokens(required): Enter the maximum number of tokens that can be generated, within 100 to 8,000 (required) Temperature(required): Set the creativity level of the generated dialogue within 0.0 to 2.0 (higher values near 2.0 increase creativity) Top-p Sampling(required): Set the selection range for the next word within 0.0 to 1.0 (e.g., 0.9 means the next word is chosen only from candidates whose cumulative probability is within 0.9, increasing sentence creativity) Prompt Safety Model(optional): Settings to restrict unethical content such as violence, hateful speech, or personal data leakage System Prompt: Think(optional): Configure the model to internally perform complex reasoning steps before producing the final answer For detailed information on parameter settings, see Setting Parameters
   Input	Number of tokens input to inference
   output	Number of tokens generated in inference
   latency	Time taken to generate the token
   Delete conversation	Delete all conversation content in the chat area
   Copy conversation	Copy the entire conversation content in the chat area
   Model comparison	You can compare two models to verify When comparing models, the conversation display area is split into two, and the PlayGround is shown for each model
   Conversation display area	Display the input content and generated conversation content in speech bubble format Click the Copy button of the speech bubble to copy only that content
   Chat input area	Enter the test content within 1,000 characters

   Table. PlayGround screen information

Terminate inference

Terminate Serverless Inference

To cancel Serverless Inference, follow the steps below.

1. All Services > AI-ML > Simple AI Inference Click the menu. 1. Navigate to the Service Home page of Simple AI Inference.
2. On the Service Home page, click the Serverless Inference menu. 2. Serverless Inference List Navigate to the page.
3. On the Serverless Inference List page, click the Cancel Service button for the Serverless Inference you want to delete.
4. When the pop-up notifying service termination opens, enter the service name and click the Confirm button.