Quick answer
Perplexity API documents search api throughput as 50 requests per second with a 50-request burst. Search uses a leaky bucket and is independent of the account's usage tier.
Verified Aug 22, 2026Official source
Current limits
| Constraint | Current value | Scope | Verified source |
|---|---|---|---|
| Search API throughputSearch uses a leaky bucket and is independent of the account's usage tier. | 50 requests per second with a 50-request burst | All usage tiers | PerplexityAug 22, 2026 |
Why does this limit matter?
A client may send the documented burst immediately but must respect the long-run refill rate.
This value is scoped to All usage tiers; a different plan, runtime, model, endpoint, region, or account can produce a different effective constraint.
What should you check?
- Separate Search endpoint metrics from other Perplexity APIs and back off on 429.
- Confirm the exact plan, model, runtime, endpoint, region, and account that serve the failing workload.
- Record the observed value, response headers or configuration, timestamp, and source without logging secrets.
Important caveats
- This value applies to POST /search, not Agent or Sonar endpoints.
- Treat the official source and live account configuration as authoritative if they differ from this verified snapshot.
HyperObserve reports the documented platform constraint. Your application, SDK, gateway, provider, region, or account can impose a lower effective limit.
Related