Beta Pricing

Simple, Transparent Pricing

Start free during beta and scale as you grow. Pricing subject to change before GA.

Free

Perfect for experimenting and prototyping

$0forever
  • 100K inference requests/month
  • 3 model deployments
  • Community support
  • Basic monitoring
  • Shared compute
Most Popular

Pro

For production workloads and growing teams

$99/month
  • 1M inference requests/month
  • Unlimited deployments
  • Priority support
  • Advanced monitoring & alerts
  • Dedicated compute
  • Custom domains
  • Team collaboration
  • Auto-scaling

Enterprise

For large-scale deployments with custom needs

Custom
  • Unlimited inference requests
  • Unlimited deployments
  • Dedicated support & SLAs
  • Custom integrations
  • Private cloud / On-premise
  • SOC 2 & HIPAA compliance
  • Volume discounts
  • Custom contracts

Frequently Asked Questions

What counts as an inference request?

Each API call to generate a response from a model counts as one inference request, regardless of input or output size.

Is the pricing final?

This is beta pricing and may change before general availability. Early adopters will be notified of any changes in advance.

Do unused requests roll over?

Free tier requests reset monthly. Pro plan terms will be finalized before GA. Enterprise customers can negotiate custom terms.

What happens if I exceed my limit?

During beta, we'll notify you as you approach your limit. You can request a limit increase or upgrade your plan.

Is there a free trial for Pro?

During beta, all features are available with generous limits. Pro plan trials will be available at GA.

What payment methods will you accept?

We plan to accept all major credit cards, ACH transfers, and wire transfers for Enterprise customers at launch.