Scale on Demand.

Pay for exactly what your vectors compute.

Hobby

$0/mo

Perfect for experimenting with RAG.

  • 10,000 queries / mo
  • Community Support
  • Shared cluster
Most Popular

Pro

$49/mo

For production startup applications.

  • 1M queries / mo
  • 1ms guaranteed latency
  • Email SLA

Enterprise

Custom

Dedicated NVIDIA H100 pods.

  • Unlimited scale
  • SOC2 + HIPAA compliant
  • 24/7 Slack channel
Exit to Full Portfolio