Skip to main content
Fireworks AI uses a usage-based pre-paid model for new self-serve accounts. You purchase credits, then usage is deducted based on:
  • Per token for serverless inference
  • Per GPU usage time for on-demand deployments
  • Per token of training data for fine-tuning
Billing model by account type:
  • Accounts created before June 1 keep their existing postpaid terms (grandfathered).
  • Enterprise accounts can be configured for postpaid billing on request.
For customers needing enterprise-grade security and reliability, please reach out to us at inquiries@fireworks.ai to discuss options. Find out more about our current pricing on our Pricing page.