Pricing
Start free. Scale when you're ready.
Predictable tiers for every stage. No egress surprises, no hidden fees — just compute, hosting, and API access at a fair price.
Pricing
Start free, scale when you're ready
No surprise bills. Pay for what you use, with predictable monthly tiers for growing teams.
Starter
No credit card required
- 50 GPU-hours / month
- 5 hosted model endpoints
- Community support
- Shared inference cluster
- 99.9% uptime SLA
Growth
per month, billed monthly
- 500 GPU-hours / month
- 50 hosted model endpoints
- Email & Slack support
- Dedicated inference nodes
- 99.99% uptime SLA
- Custom model fine-tuning
Enterprise
Volume pricing available
- Unlimited GPU-hours
- Unlimited model endpoints
- Dedicated Slack + SRE
- VPC & private networking
- Custom SLA guarantees
- SOC 2 / HIPAA / BAA
All plans include the Kybra CLI, SDK access, and the developer playground. Compare full feature list →
Starter
Growth
Enterprise
Compute
GPU-hours / month
50
500
Unlimited
GPU types
L40S
A100, L40S
H100, A100, L40S
Multi-node training jobs
Spot instance pricing
Reserved instance pricing
Real-time GPU telemetry
Model Hosting
Hosted model endpoints
5
50
Unlimited
Custom model weights
Version pinning
Rolling deployments
Fine-tuning support
Private endpoints (mTLS)
API
Inference requests / min
60
1,000
Unlimited
Streaming (SSE)
Batch inference
Function calling
OpenAI-compatible API
Playground access
Support
Support channel
Community
Email + Slack
Dedicated SRE
Response time SLA
Best effort
< 8 hours
< 1 hour
Uptime SLA
99.9%
99.99%
Custom
Onboarding assistance
Security
SSO / SAML
RBAC
VPC isolation
Audit logs
SOC 2 Type II
HIPAA / BAA
Your cluster is ready
in 60 seconds.
No credit card required. Scale from a single model endpoint to thousands of GPUs — at your pace.
Questions? [email protected]