Pricing

GPU Container GPU Virtual Machine Serverless Inference Dedicated Inference

USD JPY VND

H100 GPU Instance

80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia

GPU instance

Specification

Price/hour

1xGPU H100 SXM5

250GB RAM15 cores CPU1TB NVMe Temporary Disk

¥459.14

2xGPU H100 SXM5

500GB RAM30 cores CPU2TB NVMe Temporary Disk

¥918.29

3xGPU H100 SXM5

750GB RAM45 cores CPU3TB NVMe Temporary Disk

¥1,377.43

4xGPU H100 SXM5

1000GB RAM60 cores CPU4TB NVMe Temporary Disk

¥1,836.58

5xGPU H100 SXM5

1250GB RAM75 cores CPU5TB NVMe Temporary Disk

¥2,295.72

6xGPU H100 SXM5

1500GB RAM90 cores CPU6TB NVMe Temporary Disk

¥2,754.87

7xGPU H100 SXM5

1750GB RAM105 cores CPU7TB NVMe Temporary Disk

¥3,214.01

8xGPU H100 SXM5

2000GB RAM120 cores CPU8TB NVMe Temporary Disk

¥3,673.16

H200 GPU Instance

141 GB HBM3 Memory· Intel Xeon Platinum 8558 · Japan

GPU instance

Specification

Price/hour

1xGPU H200 SXM5

250GB RAM20 cores CPU1TB NVMe Temporary Disk

¥1,013.50

2xGPU H200 SXM5

500GB RAM40 cores CPU2TB NVMe Temporary Disk

¥2,026.99

3xGPU H200 SXM5

750GB RAM60 cores CPU3TB NVMe Temporary Disk

¥3,040.49

4xGPU H200 SXM5

1000GB RAM80 cores CPU4TB NVMe Temporary Disk

¥4,053.98

5xGPU H200 SXM5

1250GB RAM100 cores CPU5TB NVMe Temporary Disk

¥5,067.48

6xGPU H200 SXM5

1500GB RAM120 cores CPU6TB NVMe Temporary Disk

¥6,080.98

7xGPU H200 SXM5

1750GB RAM140 cores CPU7TB NVMe Temporary Disk

¥7,094.47

8xGPU H200 SXM5

2000GB RAM160 cores CPU8TB NVMe Temporary Disk

¥8,107.97

Storage

Storage type

Specification

Location

Price (GB/hour)

Persistent Storage

Suitable for storing data, models, or files that need to be retained even the instance is halted or rebooted. Billed by 1 GB

Southeast Asia, Japan

¥0.04

Bundled with GPU, CPU, RAM and 2 Storage type offerings, with 01 Public IP included

Local Storage Block Storage

NVIDIA B300 Ultra SXM

288 GB HBM3 memory per GPU · Dual 6th Gen Intel Xeon · Southeast Asia

GPU VM

Specification

Price/hour

1xGPU B300 SXM

192GB RAM28 vCPU3TB Local Storage NVMe

¥1,073.38

2xGPU B300 SXM

384GB RAM56 vCPU6TB Local Storage NVMe

¥2,146.77

4xGPU B300 SXM

768GB RAM112 vCPU12TB Local Storage NVMe

¥4,293.54

8xGPU B300 SXM

1536GB RAM224 vCPU24TB Local Storage NVMe

¥8,587.08

NVIDIA H100 SXM5

80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia

GPU VM

Specification

Price/hour

1xGPU H100 SXM5

192GB RAM16 vCPU3TB local storage NVMe

¥459.14

2xGPU H100 SXM5

384GB RAM32 vCPU6TB Local Storage NVMe

¥918.29

4xGPU H100 SXM5

768GB RAM64 vCPU12TB Local Storage NVMe

¥1,836.58

8xGPU H100 SXM5

1536GB RAM128 vCPU24TB Local Storage NVMe

¥3,673.16

NVIDIA H200 SXM5

141 GB HBM3 Memory· Intel Xeon Platinum 8558 · Japan

GPU VM

Specification

Price/hour

1xGPU H200 SXM5

192GB RAM24 vCPU3TB Local Storage NVMe

¥1,013.50

2xGPU H200 SXM5

384GB RAM48 vCPU6TB Local Storage NVMe

¥2,026.99

4xGPU H200 SXM5

768GB RAM96 vCPU12TB Local Storage NVMe

¥4,053.98

8xGPU H200 SXM5

1536GB RAM192 vCPU24TB Local Storage NVMe

¥8,107.97

Network Volume

Storage type

Specification

Location

Price (GB/hour)

Network Volume

Suitable for storing data, models, or files that need to be retained even when the instance is halted or rebooted. Billed by 1 GB

Southeast Asia, Japan

¥0.04

NVIDIA RTX PRO 6000 Blackwell

96GB of HBM3 memory . Dual 6th Gen Intel Xeon Scalable . Southeast Asia

GPU VM

Specification

Price/hour

1xGPU RTX PRO 6000 Blackwell

192GB RAM28 vCPU3TB Temporary Storage NVMe

¥336.14

2xGPU RTX PRO 6000 Blackwell

384GB RAM56 vCPU7TB Temporary Storage NVMe

¥672.29

4xGPU RTX PRO 6000 Blackwell

576GB RAM84 vCPU14TB Temporary Storage NVMe

¥1,344.57

8xGPU RTX PRO 6000 Blackwell

768GB RAM112 vCPU28TB Temporary Storage NVMe

¥2,689.14

GPU A30 Ampere

24GB of memory. Southeast Asia

GPU VM

Specification

Price/hour

1xGPU A30 Ampere

32GB RAM16vCPUBundle 50GB Block storage Standard

¥162.77

NVIDIA H100 SXM5

80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia

GPU VM

Specification

Price/hour

1xGPU H100 SXM5

192GB RAM16 vCPU50GB Block storage - Standard tier bundled

¥459.14

2xGPU H100 SXM5

384GB RAM32 vCPU100GB Block storage - Standard tier bundled

¥918.29

4xGPU H100 SXM5

768GB RAM64 vCPU200GB Block storage - Standard tier bundled

¥1,836.58

8xGPU H100 SXM5

1536GB RAM128 vCPU400GB Block storage - Standard tier bundled

¥3,673.16

NVIDIA H200 SXM5

141 GB HBM3 Memory· Intel Xeon Platinum 8558 · Japan

GPU VM

Specification

Price/hour

1xGPU H200 SXM5

192GB RAM24 vCPU50GB Block storage - Standard tier bundled

¥1,013.50

2xGPU H200 SXM5

384GB RAM48 vCPU100GB Block storage - Standard tier bundled

¥2,026.99

4xGPU H200 SXM5

768GB RAM96 vCPU200GB Block storage - Standard tier bundled

¥4,053.98

8xGPU H200 SXM5

1536GB RAM192 vCPU400GB Block storage - Standard tier bundled

¥8,107.97

Storage (Additional)

Billed by 1 GB. Scale up for the Boot volume or attach one more Data volume

Storage type

Specification

Location

Price (GB/hour)

Block Storage - Standard tier

Ideal for lightweight AI/ML, infrequent data access, small datasets.

Southeast Asia, Japan

¥0.03

Block Storage - Premium tier

Suitable for distributed training, large datasets, multiple AI inference requests.

Southeast Asia, Japan

¥0.06

Network Volume

Storage type

Specification

Location

Price (GB/hour)

Network Volume

Suitable for storing data, models, or files that need to be retained even when the instance is halted or rebooted. Billed by 1 GB

Southeast Asia, Japan

¥0.04

Vision Language Model

Model name

Context length

Input price

Output price

Cached price

Unit

Qwen3.8-27B

262K

¥69.102

¥491.392

¥7.678

million tokens

gemma-4-26B-A4B-it

262K

¥21.4984

¥61.424

¥7.678

million tokens

gemma-3-27b-it

128K

¥16.8916

¥25.3374

—

million tokens

Google:Gemini-3.1-Pro-Preview-Custom-Tool

~1M

¥307.12

¥1,842.72

¥3.0712

million tokens

Google:Gemini-3.5-Flash

~1M

¥230.34

¥1,382.04

¥23.034

million tokens

Alibaba:Qwen3.8-Max

~1M

¥307.12

¥921.36

¥38.39

million tokens

Minimax:Minimax-M3

~1M

¥46.068

¥184.272

¥9.2136

million tokens

gemma-4-31B-it

262K

¥23.034

¥69.102

¥13.8204

million tokens

Qwen2.5-VL-7B-Instruct

33K

¥118.2412

—

million tokens

Text Embeddings

Model name

Context length

Input price

Output price

Cached price

Unit

Vietnamese_Embedding

¥1.68916

¥0.00

—

million tokens

multilingual-e5-large

¥3.37832

¥0.00

—

million tokens

Text to Speech

Model name

Context length

Input price

Output price

Cached price

Unit

FPT.TTS-ultra

10K

¥7,678.00

¥0.00

—

million characters / minute

FPT.AI-VITs

10K

¥2,533.74

¥0.00

—

million characters / minute

FPT.TTS-pro

10K

¥2,533.74

¥0.00

—

million characters / minute

Large Language Model

Model name

Context length

Input price

Output price

Cached price

Unit

GPT-4.1

¥307.12

¥1,228.48

¥76.78

million tokens

GLM-5.2

¥214.984

¥675.664

¥39.9256

million tokens

Z.ai:GLM-5.3

~1M

¥214.984

¥675.664

¥39.9256

million tokens

gpt-oss-120b

128K

¥21.95908

¥92.9038

¥4.6068

million tokens

Alibaba:DeepSeek-V4.1-Flash

~1M

¥46.068

¥184.272

¥4.6068

million tokens

Alibaba:Deepseek V4 Pro 0813

~1M

¥202.6992

¥608.0976

¥20.26992

million tokens

Alibaba:Kimi K3

~1M

¥460.68

¥2,303.40

¥46.068

million tokens

Azure:gpt-4.1-nano

~1M

¥15.356

¥61.424

¥4.6068

million tokens

Azure:gpt-5.6-luna

1.05M

¥30.712

¥184.272

¥3.0712

million tokens

Azure:gpt-5.6-sol

1.05M

¥767.80

¥4,606.80

¥76.78

million tokens

Azure:gpt-5.6-terra

1.05M

¥307.12

¥1,842.72

¥30.712

million tokens

Z.ai:GLM-5.3 Flash

~1M

¥23.034

¥76.78

¥4.6068

million tokens

DeepSeek-V4-Flash

200K

¥21.4984

¥42.9968

¥2.76408

million tokens

Z.ai:GLM-5.2

~1M

¥214.984

¥675.664

¥39.9256

million tokens

Llama-3.3-70B-Instruct

32K

¥32.09404

¥69.25556

¥23.034

million tokens

Qwen3.6-27B

262K

¥46.068

¥499.07

¥23.034

million tokens

Reranking

Model name

Context length

Input price

Output price

Cached price

Unit

bge-reranker-v2-m3

¥3.37832

¥0.00

—

million tokens

Speech to Text

Model name

Context length

Input price

Output price

Cached price

Unit

FPT.AI-whisper-large-v3-turbo

¥4.560732

¥0.00

—

minute / million tokens

FPT.AI-whisper-medium

¥2.53374

¥0.00

—

minute / million tokens

whisper-large-v3-turbo

¥0.675664

¥0.00

—

minute / million tokens

omni-modal

Model name

Context length

Input price

Output price

Cached price

Unit

Alibaba:Qwen3.8-Omni-Flash

~1M

¥23.034

¥72.1732

¥2.45696

million tokens

Pay-per-GPU-hour for the underlying instance hosting your deployed model. Token usage is included — no extra per-token charge. Billing: per-minute · minimum 60 seconds · rounded up

H100 GPU Instances

GPU instance

Specification

Price/hour

1xGPU H100 SXM5

250GB RAM15 cores CPU1TB NVMe Temporary Disk

¥568.17

2xGPU H100 SXM5

500GB RAM30 cores CPU2TB NVMe Temporary Disk

¥1,136.34

3xGPU H100 SXM5

750GB RAM45 cores CPU3TB NVMe Temporary Disk

¥1,704.52

4xGPU H100 SXM5

1000GB RAM60 cores CPU4TB NVMe Temporary Disk

¥2,272.69

5xGPU H100 SXM5

1250GB RAM75 cores CPU5TB NVMe Temporary Disk

¥2,840.86

6xGPU H100 SXM5

1500GB RAM90 cores CPU6TB NVMe Temporary Disk

¥3,409.03

7xGPU H100 SXM5

1750GB RAM105 cores CPU7TB NVMe Temporary Disk

¥3,977.20

8xGPU H100 SXM5

2000GB RAM120 cores CPU8TB NVMe Temporary Disk

¥4,545.38

Storage

Storage type

Specification

Location

Price (GB/hour)

Persistent Storage

Suitable for storing data, models, or files that need to be retained even the instance is halted or rebooted. Billed by 1 GB

Southeast Asia, Japan

¥0.04