No minimums, no lock-in. Free to start, then a flat rate per token.
For prototyping and side projects.
For teams shipping AI in production.
Dedicated clusters, VPC and compliance.
| Free | Pro | Enterprise | |
|---|---|---|---|
| Tokens / month | 1M | Unlimited | Unlimited |
| Cold start | 8ms | 8ms | 8ms |
| Fine-tuning | — | ✓ | ✓ |
| Autoscaling | — | ✓ | ✓ |
| Dedicated clusters | — | — | ✓ |