Pricing

Transparent pricing. No hidden fees. Pay per usage.

Free

€0

Free queue: ~20s

  • 100k tokens/month
  • 1 hour compute
  • API access

Starter

€9/month

Priority queue

  • 500k tokens/month
  • 5 hours compute
  • Priority queue
  • Email support

Pro

€19/month

Pro queue: instant

  • 1M tokens/month
  • 10 hours CPU compute
  • 2 hours GPU/month included
  • Extra GPU: €0.50/hour
  • Priority support

Enterprise

Custom

  • Unlimited usage
  • GPU deployment
  • Dedicated SLA
  • Custom deployment

Deploy with GPU

Run larger models and faster inference with NVIDIA GPU. Pro includes 2h GPU/month; extra hours at €0.50/hr. Enterprise: dedicated capacity.

Enterprise GPU →