Account quotas ↗
noOriginal Documentation
Documentation Index#
Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt Use this file to discover all available pages before exploring further.
Account-wide request limits, spending tiers, budget controls, and on-demand GPU quotas
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:
firectl quota listThis 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:
| Tier | Criteria | Max Monthly Budget |
|---|---|---|
| Tier 1 | Valid payment method and billing profile | $50 |
| Tier 2 | Spend or add $50 in credits | $500 |
| Tier 3 | Spend or add $500 in credits | $5,000 |
| Tier 4 | Spend or add $5,000 in credits | $50,000 |
| Unlimited | Contact us | Unlimited |
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.
New self-serve accounts use pre-paid billing by default. Accounts created before June 1 remain grandfathered on postpaid terms. Enterprise accounts can request postpaid billing.
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:
| Account state | Request-rate limit |
|---|---|
| No payment method or no credits | 10 RPM |
| Payment method and active credits | 6,000 RPM (maximum) |
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:
firectl quota listSet a custom monthly budget:
firectl quota update monthly-spend-usd --value <AMOUNT>For example, to set a $200 monthly budget:
firectl quota update monthly-spend-usd --value 200When 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:
| GPU Type | Default Quota |
|---|---|
| Nvidia A100 | 8 GPUs |
| Nvidia H100 | 8 GPUs |
| Nvidia H200 | 8 GPUs |
| Nvidia B200 | 8 GPUs |
| LoRAs (on-demand) | 100 |
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:
- Go to Billing
- Resolve failed payment methods and add credits (or pay outstanding invoices for postpaid accounts)
- Your account reactivates automatically within an hour
Still suspended after resolving payment issues? Contact support via Discord or email inquiries@fireworks.ai.