FAQs
Answers, simplified.
Got Questions?
We’ve Got Answers.
Whether you’re just getting started or already a pro, our FAQ section covers everything you need—from billing to features. Everything to make your experience smoother.
View All
Using Arkane Cloud
Billing & Payment
Security & Data
How do I get started with Arkane Cloud?
Sign up for your account, verify your email, and access our dashboard within minutes. Choose between GPU instances for custom workloads or AI endpoints for immediate model access. Our quick-start guide walks you through your first deployment in under 10 minutes.
What GPU types and configurations are available?
We offer NVIDIA B300, B200, H200, H100, A100, L40S GPUs in various configurations from single GPU instances to multi-node clusters.
Real-time availability is shown in our dashboard.
Real-time availability is shown in our dashboard.
What storage options are available for datasets and models?
High-performance NVMe storage attached to GPU instances, with options for persistent volumes that survive instance restarts.
Shared storage available for multi-node training jobs.
Shared storage available for multi-node training jobs.
How do I manage costs and optimize my spending?
Real-time cost tracking with detailed breakdowns by resource type and project. Budget alerts, spending limits. Reserved capacity discounts for for flexible workloads.
How is GPU usage billed?
We offer two billing models: on-demand GPU servers are billed by minute for the time your server instance is active, while our API endpoints for text and image generation are billed respectively per tokens and per image.
For GPU servers, you pay from the moment you spin up an instance until you terminate it.
For API inference, you're charged only for successful generation requests. No ongoing server costs or idle time charges.
For GPU servers, you pay from the moment you spin up an instance until you terminate it.
For API inference, you're charged only for successful generation requests. No ongoing server costs or idle time charges.
Do you offer volume discounts?
Yes, we provide tiered pricing depending of commitment.
Higher volume customers can also access enterprise pricing with custom rates, dedicated support, and flexible billing terms.
Contact our sales team for volume pricing above certain thresholds.
Higher volume customers can also access enterprise pricing with custom rates, dedicated support, and flexible billing terms.
Contact our sales team for volume pricing above certain thresholds.
What GPU types are available and how do they affect pricing?
We offer various GPU tiers from cost-effective options for lighter workloads to high-performance GPUs for demanding applications.
Pricing varies by GPU type, you can choose the optimal GPU type based on your performance and budget requirements.
Pricing varies by GPU type, you can choose the optimal GPU type based on your performance and budget requirements.
Are there any setup fees or minimum commitments?
Our pay-as-you-go model has no setup fees or minimum monthly commitments. You can start with as little as a few API calls.
However, reserved instances and enterprise plans may have minimum commitments in exchange for significant cost savings.
However, reserved instances and enterprise plans may have minimum commitments in exchange for significant cost savings.
How do you protect my data and models?
All data is encrypted in transit and at rest using industry-standard AES-256 encryption. We implement zero-trust network architecture, and your data is never used to train our models or shared with other customers. Each customer environment is isolated with dedicated compute resources and secure API endpoints.
What enterprise features and support do you provide?
Enterprise customers receive dedicated account management, priority support with guaranteed response times, custom SLAs, and access to beta features.
We also offer cluster solutions, custom training, and integration assistance with your existing infrastructure and workflows.
We also offer cluster solutions, custom training, and integration assistance with your existing infrastructure and workflows.
How do you compare to other AI service providers?
Unlike larger providers, we specialize exclusively in AI inference with optimized infrastructure and competitive pricing. We offer more flexible deployment options, faster response times, and personalized support.
Our focus on both GPU servers and API endpoints gives you more control over your AI workloads than API-only providers.
Our focus on both GPU servers and API endpoints gives you more control over your AI workloads than API-only providers.
Is my data used to train or improve your models?
Absolutely not. Your prompts, generated content, and usage patterns are never used to train, fine-tune, or improve any AI models. All customer data remains completely separate from our model development processes and is never shared with third parties.
How is data isolated between GPU instances and tenants?
Each GPU instance runs in completely isolated containers with dedicated memory allocation and no shared storage. Multi-tenant GPU servers use hardware-level isolation and secure boot processes. Private GPU clusters provide physical hardware isolation for maximum security.
How do you secure GPU clusters for training sensitive datasets?
Training clusters use encrypted storage volumes, secure data pipelines, and network isolation. Private clusters can be deployed in your VPC with custom firewall rules. Data never persists on GPU instances after training completion unless explicitly configured.
What network security controls are available for GPU clusters?
GPU clusters support VPN connectivity, private networking, IP whitelisting, and custom firewall rules. Enterprise deployments include DDoS protection, intrusion detection systems, and network traffic analysis for threat monitoring.
Load More