Platform hub

Perplexity API limits

Agent, Search, and Sonar API rate limits across permanent spend tiers. Values below are scoped rather than flattened into one misleading platform-wide number.

Verified Aug 22, 2026Official docs
Quick answer:  Perplexity API has multiple independent constraints. Match the exact plan, model, runtime, invocation mode, or server configuration shown in each row.

Current documented limits

ConstraintCurrent valueScopeVerified source
Agent API tier rangeThe same tiers range from 1 to 33 queries per second.Tier 0: 50 RPM; Tiers 4–5: 2,000 RPMPermanent cumulative-spend tiersPerplexityAug 22, 2026
Search API throughputSearch uses a leaky bucket and is independent of the account's usage tier.50 requests per second with a 50-request burstAll usage tiersPerplexityAug 22, 2026
Sonar model RPMDeep Research, Sonar, and asynchronous endpoints each have separate values.Tier 0: 5–50 RPM; upper tiers: up to 100–4,000 RPMModel and tier specificPerplexityAug 22, 2026
cumulative credit thresholdsOnce reached, tiers are retained and do not downgrade.Tier 1 at $50; Tier 5 at $5,000 cumulative creditsAPI accountsPerplexityAug 22, 2026

How to apply Perplexity API limits safely

The monitored baseline covers Agent API tier range, Search API throughput, Sonar model RPM, cumulative credit thresholds. Treat these as separate constraints rather than one platform-wide capacity number: a workload can fit one row and still fail another because the plan, model, endpoint, runtime, region, invocation mode, or account scope differs.

  1. Match the production workload to the exact scope printed beside each value and confirm it in the active Perplexity API console, configuration, or response headers.
  2. Measure the serialized request, token volume, duration, concurrency, storage, or connection demand at realistic percentiles, then preserve headroom for bursts and retries.
  3. Check every adjacent layer—client, SDK, gateway, proxy, queue, database, and downstream service—for a smaller effective limit before changing architecture.

Specific limit pages

These pages exist because the constraint has a distinct implementation or troubleshooting intent. Closely related keyword variations stay consolidated.

Compare alternatives

Official sources

View Perplexity API change history