402 error with the message You exceeded your current quota, please check your plan and billing details means your organization has used up its Inference allowance or reached its spending cap. This article explains why the error occurs and how to restore access to Serverless Inference.
Why this happens
Each Forge plan includes an Inference allowance and a default spending cap. This error occurs in the following cases:- Your organization has used up its included Inference allowance and pay-as-you-go isn’t active. This applies to Free and Academic plans.
- Your organization has reached its spending cap.
Restore access
To restore access to Serverless Inference, do any of the following:- Check your allowance and usage. Open the Billing page for your organization in Forge to see the allowance available and your usage against it.
- Activate pay-as-you-go or upgrade your plan. On Free and Academic plans, in the Pay-as-you-go panel of the Billing page, activate pay-as-you-go for Inference, or upgrade your plan. See Activate pay-as-you-go.
- Raise your spending cap. If your organization has reached its spending cap, contact your account executive or Support.
Quotas & Rate Limits Billing