Overview

1: ServiceWatch metric

Service Overview

Simple AI Inference is a serverless service that provides various global foundation models as APIs, offering public or private environments so that LLMs can be used on internal Samsung Cloud Platform resources or externally. By using Simple AI Inference, you can use multiple LLM models through the same API and improve productivity in AI application service development. It also supports compatibility with OpenAI and the LangChain SDK, enabling easy integration with existing development environments and frameworks.

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 charged based on the actual usage of input (Input) and output (Output) tokens.
Stable Service Provision: We provide stable services through traffic control (TPM/RTM).
Enterprise security provided: Data is securely protected in a rigorous security environment and is not used for external model training.

Service architecture diagram

Provided Features

Simple AI Inference provides the following features.

Check convenient LLM model
- You can easily view the features and primary use cases of LLM models provided through the LLM model catalog.
- You can view and test the provided LLM model directly on the console screen using PlayGround.
  Reference
  PlayGround is scheduled to be offered after September 2026.
Shared Use of LLM Model Account: If you request a model to use in Simple AI Inference, all users within the same Account can use it.
Serverless Service Provision : Users can request the desired model via an API and use it immediately without managing resources, and they pay only for what they use.
Public/Private endpoint provision: Depending on the user’s inference usage pattern, you can choose to use either a Public or Private endpoint.
Stable Service Provision: We provide a stable service environment through traffic control (TPM/RPM).

Provided model

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

Model name	Application	Input type	TPM	RPM	Context Size	Image input limit count
Qwen3.6-27B	Text, Agent	Text, Image	1,000,000	100	262,144	8
gemma-4-31B-it	Text, Agent	Text, Image	1,000,000	100	262,144	8
gpt-oss-120b	Text	Text	1,000,000	100	131,072	-
Llama-Guard-4-12B	Security	Text, Image	1,000,000	250	307,200	8
Qwen3-VL-Embedding-8B	embedding	Text, Image	1,000,000	250	262,144	8
Qwen3-VL-Reranker-8B	reranker	Text, Image	1,000,000	250	262,144	8

Table. Simple AI Inference provided LLM model

Caution

The models provided by the Simple AI Inference service are results generated in-house based on the data used to train the AI model. Therefore, the content, opinions, values, and judgments generated by the model are entirely unrelated to the official position or intent of Samsung Cloud Platform. Additionally, due to the nature of AI models, responses may contain distorted information or errors (hallucinations); therefore, when making important decisions, you should always verify the facts separately.

Provision status by region

The regions that provide Simple AI Inference service are as follows.

Region	Provision status
Korea West (kr-west1)	Provide
Korea East (kr-east1)	Not provided
South Korea 1 (kr-south1)	Not provided
South Korea South 2 (kr-south2)	Not provided
South Korea South 3 (kr-south3)	Not provided

Table. Simple AI Inference Availability by Region

Preceding Service

There are no services that need to be pre-configured before creating this service.

1 - ServiceWatch metric

Simple AI Inference sends metrics to ServiceWatch. The metrics provided by default monitoring are data collected at 5‑minute intervals.

Reference

For checking metrics in ServiceWatch, see the ServiceWatch guide.

Basic Metrics

The following are the basic metrics for the Simple AI Inference namespace. The indicators whose names are displayed in bold below are the key indicators selected among the default indicators provided by Simple AI Inference. The key metrics are used to build service dashboards that are automatically created for each service in ServiceWatch. Each metric provides guidance in the user guide on which statistical values are meaningful when querying that metric, and among the meaningful statistics, the values shown in bold are the primary statistics.

In the service dashboard or monitoring tab, you can view key metrics through primary statistical values. Or you can also view the key metrics on the monitoring tab of the Simple AI Inference detail page. You can also view the usage rate per GPU device in the ServiceWatch metrics menu.

Performance item (metric name)	Detailed description	unit	meaningful statistics
Model Total Tokens	Model token usage (total)	Count	Total
Model Request Server Error	Number of model request failures (server error)	Count	total
Model Input Tokens	Model token usage (input)	Count	Total
Model Request Throttled	Model request limit count (request quota exceeded)	Count	Total
Model Request Client Error	Model request failure count (client error)	Count	Total
Model Output Tokens	Model token usage (output)	Count	total
Model Cached Tokens	Model token usage (cache)	Count	Total
Model Request Prompt Rejected	Number of model request rejections (prompt review)	Count	Total
Model Request Success	Number of successful model requests	Count	Total

Table. Simple AI Inference Basic Metrics