Skip to main content
Poixe AI applies rate limits to API calls to keep the platform stable and ensure fair use. Rate limits are a global, per-user quota: all model requests under your account share the same rate allowance, which the system schedules centrally.

​
What determines your rate limit

Rate limits are mainly tied to your user level (Level). New users start at Level 0, and as your cumulative top-ups raise your level, you generally get higher request rates and more capacity. You can view your level and the corresponding rate limits on the benefits page: https://poixe.com/tiers/user

​
Key concepts

  • RPM (Requests Per Minute): the maximum number of requests allowed per minute
  • Global quota: requests across all models and all endpoints are counted together (there is no separate quota per model)
  • Takes effect immediately: rate limits update automatically when your level increases, with no action required

​
What happens when you hit a limit

If you send too many requests in a short period, the system may return rate-limit errors. We recommend that you:
  • Add client-side retries (with exponential backoff)
  • Queue or throttle concurrent requests
  • For high-concurrency workloads, consider raising your level or contacting the team to evaluate your quota

​
Check current status

In the dashboard you can view model status and capacity (useful when troubleshooting throttling or congestion): https://poixe.com/model