Simple, Transparent Pricing
Plans include a monthly pool of STUs (Service Token Units) that meter all workloads. Starter 400 STU, Growth 5,000 STU, Enterprise 15,000 STU.
Learn more about STUsAccess to all public models
Includes 400 STU/month
Standard inference speed
Community support
All Starter features
Includes 5,000 STU/month
Priority inference speed
Reserved Throughput add-on available (boost concurrency/TPM)
Band-P unlock available
Email support (24h response)
All Growth features
Includes 15,000 STU/month
Access to dedicated inferencing endpoints
Model fine-tuning
Bring your own model
24/7 dedicated support
Custom SLAs
Band-P native
Included with Every Plan
Secure data residency with private hosting
Enterprise compliance standards (SOC 2, ISO 27001)
Audit-ready infrastructure with comprehensive logging
99.9% uptime SLA with proactive monitoring
Automatic scaling to handle variable workloads
Ready to Reduce Your AI Costs?
Join organisations leveraging our renewable energy infrastructure to cut AI costs by up to 60%.