Skip to main content
Fireworks uses different controls for serverless and on-demand deployments. This page is the canonical reference for spending tiers, budget controls, on-demand GPU quotas, and account-wide request limits. For serverless TPM and adaptive limits, see Serverless rate limits.

​
Check your current limits

View your account’s current quotas and limits:
This shows your rate limits, GPU quotas, spend limits, and usage across serverless and on-demand deployments.

​
Spending tiers

Your account tier determines the maximum budget you can set:
Add prepaid credits to unlock a higher tier. For example, adding $100 moves you from Tier 1 to Tier 2. Your new tier activates within minutes.
These spending tiers control both your maximum monthly budget and the maximum serverless TPM upper bounds your account can reach.Fireworks operates on a pre-paid credits billing system. Contracted customers may have the option to move to post-paid billing — contact our sales team to discuss your options.

​
Training GPU quota

Fine-tuning jobs use training GPU quota (separate from on-demand deployment quota), granted automatically by spending tier: Counts are GPUs of that type available to training jobs. Blackwell (B200/B300) is 0 until Tier 2, and current managed fine-tuning shapes run on Blackwell, so most fine-tuning needs Tier 2. If a job is rejected with HTTP 429 quota_exceeded, raise your tier and resubmit.
Need more training quota than your tier allows? Reach out for enterprise support and we’ll help size the right allocation for your workload.

​
Enterprise accounts

Enterprise accounts do not have the same spend limits. If you have an Enterprise account, the spending tiers and budget controls described on this page do not apply to you. For information about Enterprise quotas and resource allocation, see Enterprise quotas or contact your enterprise account representative.

​
Manage your quotas

​
Account-wide request limits

All API usage on your account shares a single request-throughput envelope: The 6,000 RPM cap applies account-wide—it is not a separate serverless-only limit—and it is a fixed ceiling, not adaptive. Per-minute request volume above this cap is rejected (for example HTTP 429), regardless of your spending tier.

​
Budget control

Control your monthly spending with flexible budget limits. Set a limit that fits your needs and adjust it anytime.

​
View and adjust your spend limit

Check your current spend limit:
Set a custom monthly budget:
For example, to set a $200 monthly budget:

​
When you reach your budget

When you reach your spending limit, all API requests pause automatically across serverless inference, deployments, and fine-tuning. To resume, add credits and/or raise your budget cap.
This does not apply to Enterprise accounts. Enterprise accounts do not have the same spend limits and will not be paused due to spending.

​
On-demand deployment quotas

On-demand deployments have GPU quotas instead of rate limits:
Need more GPUs? Contact us to request a quota increase.
On-demand and dedicated deployments are not limited by adaptive serverless TPM upper bounds. If you receive HTTP 429 on those endpoints, it typically means deployment saturation (GPUs busy) rather than hitting a TPM tier cap. Requests still count toward account-wide request limits. See understanding 429 errors for details and resolution steps.

​
Account recovery

If your account is suspended due to payment issues:
  1. Go to Billing
  2. Resolve failed payment methods and add credits (or pay outstanding invoices for postpaid accounts)
  3. Your account reactivates automatically within an hour
Still suspended after resolving payment issues? Contact support via Discord or email inquiries@fireworks.ai.