Licensing
Scaled for your inference cluster.
Predictable pricing for high-performance AI infrastructure.
Standard
$299/mo
- Max Model Size: 13B
- Standard Kernels
- Community Support
- API Rate Limit: 100/min
Professional
$899/mo
- Max Model Size: 70B
- Flash CUDA Kernels
- Automated Benchmarking
- Priority Processing
- Custom Calibration Data
Enterprise
Custom
- Unlimited Model Parameters
- Custom Kernel Development
- Dedicated Support SLA
- Self-Hosted Infrastructure
- Team RBAC Management