Pricing
H100 GPU Instance
80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia
GPU instance
Specification
Price/hour
Bundled with GPU, CPU, RAM and 2 Storage type offerings, with 01 Public IP included
NVIDIA B300 Ultra SXM
288 GB HBM3 memory per GPU · Dual 6th Gen Intel Xeon · Southeast Asia
NVIDIA H100 SXM5
80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia
NVIDIA H200 SXM5
141 GB HBM3 Memory· Intel Xeon Platinum 8558 · Japan
NVIDIA RTX PRO 6000 Blackwell
96GB of HBM3 memory . Dual 6th Gen Intel Xeon Scalable . Southeast Asia
GPU VM
Specification
Price/hour
GPU A30 Ampere
24GB of memory. Southeast Asia
NVIDIA H100 SXM5
80 GB HBM3 memory . Intel Xeon Platinum 8462Y+ . Southeast Asia
GPU VM
Specification
Price/hour
NVIDIA H200 SXM5
141 GB HBM3 Memory· Intel Xeon Platinum 8558 · Japan
GPU VM
Specification
Price/hour
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
Vision Language Model
Model name
Context length
Input price
Output price
Cached price
Unit
Multimodal
Model name
Context length
Input price
Output price
Cached price
Unit
Text Embeddings
Model name
Context length
Input price
Output price
Cached price
Unit
Text to Speech
Model name
Context length
Input price
Output price
Cached price
Unit
Large Language Model
Model name
Context length
Input price
Output price
Cached price
Unit
Reranking
Model name
Context length
Input price
Output price
Cached price
Unit
omni-modal
system one
Model name
Context length
Input price
Output price
Cached price
Unit
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
