Transparent Pricing
Scale your infrastructure without scaling your anxiety. Simple, tier-based pricing for every stage of growth.
Hobby
Everything you need to kickstart your ML deployments.
- 5 models deployed
- 5 GB bandwidth
- 10,000 API calls
- Basic monitoring
- Community support
Pro
PopularExpand your capabilities with robust ML infrastructure.
- 50 models deployed
- 50 GB bandwidth
- 100,000 API calls
- Real-time monitoring
- Priority support
Enterprise
Scale seamlessly with enterprise-grade solutions.
- Unlimited models
- 500 GB bandwidth
- 1,000,000 API calls
- Detailed analytics
- Custom SLAs & Compliance
Feature Comparison
| Features | Hobby | Pro | Enterprise |
|---|---|---|---|
| Deployed Models | 5 | 50 | Unlimited |
| API Calls / mo | 10k | 100k | 1M+ |
| Bandwidth | 5GB | 50GB | 500GB |
| Log Retention | 1 day | 30 days | 1 year |
| Support SLA | - | 24h Response | 1h Dedicated |
| SSO / SAML | |||
| VPC Peering | |||
| Custom Containers |
Frequently Asked Questions
What counts as an API call?
Every prediction request sent to your deployed model endpoint counts as one API call. Health checks and system pings are excluded.
Can I upgrade my plan later?
Yes, you can upgrade or downgrade your plan at any time. Changes take effect immediately with prorated billing.
What happens if I exceed my limits?
You'll be notified when reaching 90% and 100% of your quotas. Resquests will be refused after 100%, unless 'Tier-less mode' is activated. Then overages are billed at standard rates for Pro/Enterprise.
Do you offer student discounts?
Yes, students and researchers can apply for free credits. Contact our support team with your academic email.
Is my data secure?
We use AES-256 encryption at rest and TLS 1.3 in transit. We are SOC2 Type II compliant.
Can I deploy on my own cloud?
Yes, Enterprise plans support BYOC (Bring Your Own Cloud) for AWS, GCP, and Azure.