The page has been translated by Gen AI.

Overview

Service Overview

Simple AI Inference is a serverless service that provides various global foundation models via API, offering public or private environments to use LLMs with internal resources on the Samsung Cloud Platform or from external sources. Using Simple AI Inference allows you to use multiple LLM models through the same API, improving the development productivity of AI application services. It also supports compatibility with the OpenAI and LangChain SDKs, enabling seamless integration with existing development environments and frameworks.

Key Features

Convenient LLM model usage: As a fully managed serverless service, you can use multiple LLM models through the same API.
Efficient Cost Management: Costs are billed based on the actual usage of input and output tokens.
Stable service delivery: We provide stable services through traffic control (TPM/RTM).
Enterprise-grade security: Data is securely protected in a rigorous security environment and is not used for external model training.

Service Architecture Diagram

Features

Simple AI Inference provides the following features.

Convenient LLM Model Verification
- You can easily review the features and key use cases of LLM models provided through the LLM model catalog.
- You can use PlayGround to view and test the provided LLM models directly from the console screen.
Shared Account Access for LLM Models: When you request a model for use in Simple AI Inference, all users within the same account can access it.
Serverless service offering: Users can request and immediately use the desired model via the API without managing resources, and they are billed only for what they use.
Public/Private Endpoint Provision: You can select and use either a public or private endpoint based on your inference usage patterns.
Stable service delivery: Provides a stable service environment through traffic control (TPM/RPM).

Provided Model

The LLM models provided by Simple AI Inference are as follows:

Model Name	Use Cases	Input Type	TPM	RPM	Precision	Context Size	Image input limit
Qwen3.6-27B	Text, Agent	Text, Image	10,000,000	100	FP8	262,144	8
Qwen3.8-27B	Text, Agent	Text, Image	10,000,000	100	FP8	262,144	8
gemma-4-31B-it	Text, Agent	Text, Image	10,000,000	100	FP8	262,144	8
gpt-oss-120b	Text	Text	10,000,000	100	FP4	131,072	-
Llama-Guard-4-12B	Security	Text, Image	10,000,000	250	FP16	614,400	8
Qwen3-VL-Embedding-8B	embedding	Text, Image	10,000,000	250	FP8	262,144	8
Qwen3-VL-Reranker-8B	reranker	Text, Image	10,000,000	250	FP8	262,144	8

Table. LLM models provided by Simple AI Inference

Warning

The models provided by the Simple AI Inference service are outputs generated by the AI model based on its learned data. Therefore, the content, opinions, values, and judgments generated by the model are entirely unrelated to the official stance or intent of Samsung Cloud Platform. Additionally, due to the nature of AI models, responses may contain distorted information or errors (a phenomenon known as hallucination). Therefore, when making important decisions, you must independently verify the facts.

Provided Status by Region

The following are the Litions that provide the Simple AI Inference service.

Legion	Availability
Korea West (kr-west1)	Provided
Korea East (kr-east1)	Not provided
South Korea 1 (kr-south1)	Not provided
South Korea 2 (kr-south2)	Not provided
South Korea 3 (kr-south3)	Not provided

Table. Simple AI Inference availability by region

Preceding Service

There are no services that must be configured before creating this service.

AI-ML

ServiceWatch metric