Starter
$
0
/mo
- One active model endpoint
- 10K inference calls per month
- Community support forum
- Standard latency tier
- API access & SDK
Popular
Pro
$
20
/seat /mo
- Unlimited model endpoints
- 500K inference calls per month
- Priority compute routing
- Custom fine-tuning pipelines
- Team dashboards & analytics
- Email support, 4hr SLA
Enterprise
Custom
pricing
- Everything in Pro
- Dedicated GPU cluster
- 99.99% uptime SLA
- On-prem deployment option
- Custom contract & billing