Skip to main content

Understanding Rate Limiting

Distinguish pending usage checks, credit limits, provider throttles and execution safeguards.

Understanding rate limiting

Rate limiting is a protective state that can temporarily restrict credit-consuming activity when a tenant, user role, model, or high-volume request reaches an applicable usage limit.

The most common reason is that a tenant has used its monthly credit allowance. Limits can also depend on role-level credit controls, the model selected, or the type of request being run.

What happens when rate limiting is active?

Users may see reduced access to AI actions that consume credits. Depending on the situation, this can include:

  • Some models being unavailable or marked as restricted

  • Workflow, app, or agent runs failing with a usage or limit message

  • File actions, tool actions, or API requests being paused or rejected

  • A user being blocked by a role-level limit even when other users in the tenant still have access

The exact behavior can vary by feature and configuration. If a limit message looks unexpected, collect the details in the support checklist below.

Tenant limits and role limits

Tenant credit limits apply to the tenant's shared monthly allowance. When the tenant allowance is reached, multiple users and AI features may be affected until the calendar-month allowance resets, the package is upgraded, or Extra Usage is enabled for an eligible organization.

Role-level limits apply independently to each assigned user. Review both weekly and monthly periods: a user can reach a personal limit while the workspace still has credits. Check the affected user’s notice and reset time.

How will users know?

Users may see in-product banners or messages, unavailable models, failed workflow runs, disabled chat submission, or API errors that reference usage limits or rate limiting.

Admins can review the dashboard, tenant management, billing-period usage, and users and roles views available to their role. Admins may also receive email notifications when tenant usage approaches or reaches the monthly allowance.

Availability of alerts and notifications can vary by tenant configuration, user role, and feature. Check the usage views to identify which limit was reached.

Can users still log in?

Sign-in generally remains available during a credit restriction so users and administrators can review usage. The notice shown explains which AI requests are restricted.

  • If the user has reached their monthly usage limit, Hatz can block further requests and ask them to contact an administrator.

  • If only the selected model is restricted, Hatz may use Auto or ask the user to choose an available model when the organization allows it.

Which requests remain available depends on the active limit and the models allowed by the organization. If the message is unclear, save the exact wording and ask an administrator to check current usage and model policy.

When does rate limiting stop?

A credit restriction can clear when its period resets or an authorized administrator adjusts the relevant role limit, package or Extra Usage budget. Provider throttles and execution safeguards require their own recovery steps. For repeated credit limits, review usage and package fit with the account owner.

If a tenant is repeatedly hitting limits before the end of the billing cycle, review the tenant's usage patterns and package fit rather than treating the event as a one-time error.

How can admins reduce the chance of rate limiting?

  • Monitor tenant and user usage after onboarding new users, workflows, integrations, or API use cases.

  • Use Auto Mode when available so Hatz can route requests to an appropriate model for the task.

  • Use the model that matches the task. Smaller models are often a better fit for simple, high-volume tasks.

  • Disable higher-multiplier models for users or groups that do not need them.

  • Keep prompts, files, and workflow inputs focused on the information needed for the task.

  • Review apps that run multiple model calls, and review workflows or agents that run multiple model calls or tool actions.

  • Use role-level credit limits when a group of users needs a defined monthly cap.

  • Review package upgrades, plan fit, or account-specific credit questions when normal usage consistently exceeds the current allowance.

How do I check credit usage?

Admins can review usage in the dashboard, tenant management, billing-period usage, and users and roles views available to their role. These views can help identify whether usage is coming from a tenant-wide pattern, a specific user, a workflow, API activity, or a recent rollout.

What if one user or workflow uses most of the credits?

Look at the model, model multiplier, files, prompt size, workflow steps, tool calls, and API activity tied to that usage. High usage can be legitimate for complex tasks, but it may also point to a workflow that should be simplified, Auto Mode that should be used, a higher-multiplier model that should be disabled for a group, or a role-level limit that should be adjusted.

What should I send support?

If you need help investigating rate limiting, create a structured support ticket and include the tenant name, affected user, date and time with timezone, feature used, model selected, workflow/app/agent name, API endpoint if applicable, exact error message or screenshot, business impact, workaround, and whether production work is blocked.

For priority guidance, see Support Severity and Priority Guide. For overage options, see Extra Usage. For the difference between usage support and billing/commercial questions, see Credits vs Billing.

Identify the kind of limit

“Checking your usage limits…” means the verdict is still pending, not that credits are exhausted. Wait for the result; contact Support if it remains stuck.

Provider throttles or access errors come from the connected service. Follow its retry guidance and check the account’s permission for the action. Hatz credits do not change provider access.

Repeated or stalled tool work: task safeguards can stop a run that is failing or making no progress. Review the completed results and narrow the remaining task. More credits do not change these safeguards. Check the outcome of any uncertain send or update before repeating it.

Check both personal periods

A role can set independent monthly and weekly limits for each user. Monthly limits reset at the start of the UTC calendar month; weekly limits reset Wednesday at noon Eastern, following daylight-saving time. A reached Block limit takes precedence over Auto-only continuation. Auto-only work still consumes credits.

When eligible package credits are exhausted, the workspace can have a shared Auto pool equal to 25% of active package credits. Enabled Extra Usage with a saved budget can restore otherwise permitted models, but personal limits still apply. See Rate Limiting and Credit Overage for the balances and alerts.

Did this answer your question?