# Unreachable RPM values on Agent API Rate Limits docs table **URL:** \ **Category:** Bug Reports\ **Tags:** agent-api, api\ **Created:** [September 19, 2026, 12:12am UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155 "2026-09-19T00:12:06Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![dev](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/dev/32/2490_2.png) [@dev](https://community.perplexity.ai/u/dev)\ **Post date:** [September 19, 2026, 12:12am UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155/1 "2026-09-19T00:12:06Z")
## Pre-flight checklist - This is about the Perplexity API, not the Perplexity app, Computer, Comet, or web UI. - I have removed API keys, secrets, and private data. - I have included enough information for someone else to reproduce the issue. ## Bug type ## **Bug type** - Other API bug - API docs issue ## Affected API area - Agent API ## Summary The [Agent API Rate Limits](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers#agent-api-rate-limits) says > The Agent API applies two independent limits to each request: the API-wide QPS limit and the Agent model’s requests-per-minute (RPM) limit. A request must be within both limits. The RPM value is not derived from the QPS value For **Tier 4** how can we ever reach `4,000/min` if the `33 QPS` is being enforced? `33*60 = 1980` Same question for Tier 5. ## Expected behavior QPS and RPM values being congruent. ## Actual behavior RPM is in theory unreachable. ---
**Author:** ![andrewmadson-pplx](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/andrewmadson-pplx/32/3428_2.png) [@andrewmadson-pplx](https://community.perplexity.ai/u/andrewmadson-pplx)\ **Post date:** [September 20, 2026, 5:15pm UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155/2 "2026-09-20T17:15:19Z")
@dev You’re right: 33 requests per second cannot sustain 4,000 requests per minute. We updated our documentation: [Rate Limits & Usage Tiers - Perplexity](https://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers#agent-api-rate-limits) Agent API does not have the separate per-model RPM. Thank you for flagging it. Andrew ---
**Author:** ![dev](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/dev/32/2490_2.png) [@dev](https://community.perplexity.ai/u/dev)\ **Post date:** [September 28, 2026, 10:28pm UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155/3 "2026-09-28T22:28:04Z")
Thanks for your answer, Andrew. Is there a strong reason for cutting down the Rate Limit in less than half for production applications? We’re noticing more rate limit hits since the migration. Is there a way to request for increase back to ~67 QPS? _pls let me know if I should open a separate ticket; also contacted API support email_ ---
**Author:** ![andrewmadson-pplx](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/andrewmadson-pplx/32/3428_2.png) [@andrewmadson-pplx](https://community.perplexity.ai/u/andrewmadson-pplx)\ **Post date:** [September 28, 2026, 11:07pm UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155/4 "2026-09-28T23:07:00Z")
Hello @dev, Please fill out a rate limit increase request for the team to review. https://perplexity.typeform.com/to/yctmfyVT?typeform-embed=embed-widget Andrew ---
**Author:** ![dev](https://sea1.discourse-cdn.com/flex001/user_avatar/community.perplexity.ai/dev/32/2490_2.png) [@dev](https://community.perplexity.ai/u/dev)\ **Post date:** [September 29, 2026, 12:22am UTC](https://community.perplexity.ai/t/unreachable-rpm-values-on-agent-api-rate-limits-docs-table/6155/5 "2026-09-29T00:22:59Z")
Thanks, @andrewmadson-pplx , Albert already responded my email.