Ambiguity on Sonar API Rate Limits docs table

Bug Reports
1

Pre-flight checklist

  • This is about the Perplexity API, not the Perplexity app, 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

  • Other API bug
    • API docs issue

Affected API area

  • Sonar API

Summary

The Sonar API Rate Limits table has 3 rows for the Models sonar, sonar-pro and sonar-reasoning-pro, all of them with 4,000 Requests per minute (RPM) for Tier 4 (production); is this a separate 4,000 RPM quota for each model independent from each other or a total shared quota between all of them? The same question applies to any tier.

Actual behavior

Table with ambiguous interpretation – see current version at Rate Limits & Usage Tiers - Perplexity

Expected behavior

Unambiguous docs table with clear expectations set, something like a *foot note should do it:

Option 1) Separate quotas

If Each model has an independent rate limit, a foot note like this could be added:

Each model has an independent RPM quota. For example, requests to sonar do not count against the RPM limit for sonar-pro or sonar-reasoning-pro

Visual sample (sugestional, not the actual page):

image
image1490×1504 318 KB

Option 2) Shared quotas

Different wording, such as

sonar, sonar-pro, and sonar-reasoning-pro all consume the same shared 4,000 RPM quota.

2

Hi! This is correct. Thanks for flagging this.

We will specify this in the docs shortly.

3

Hey @albert thanks for replying to my question! :smiley: Are you a Perplexity employee? I submitted the same question to support@perplexity.ai right after posting it here and, so far, no confirmation. Can you please reply to my email or tag a colleague to do it? I’m a Tier 4 paying customer.

Best regards and wish you a great weekend!