Catalog

Perplexity API

Perplexity data through one normalized API - per-request USD pricing, no subscriptions, and automatic failover on redundant endpoints.

Endpoints1Providers2From · search$2.00/1k req · BadgerFull breakdownRead docs
Uptime
99.22%
30d · 387 calls
Requests
387
30d · weekly, last 12 wks
Response
42.1s
median · 30d
POST

Search

Most used
/v1/run/perplexity.searchperplexity.search
Ask Perplexity a web-grounded question and receive an answer with source citations.
387 /mo
â–²11.1%
99.22%
42142ms p50
2
from$2.00/1k req
Badger

About the Perplexity API

Every provider prices each endpoint independently, so the table shows the cheapest per endpoint. Open one to compare all providers.

Measured performance

What the Perplexity API actually does

Every call through AnyAPI over the last 30 days, counted here rather than promised.

99.2%
of calls succeeded (387 calls)
Succeeded on first lane 79.3%Recovered by failover 19.9%Failed 0.8%
Response time (384 calls)
Typical (p50)
42.1s
Half of requests finish within 42.1s
p99 response time
173.7s
p99 response time: 99% of requests finish within 173.7s

FAQ

About the Perplexity API

The AnyAPI Perplexity API returns Perplexity data as normalized JSON across 1 endpoint: search. You call one endpoint per job with a single key, and AnyAPI routes each request across 2 sources, falling back automatically when one fails. Pricing is in US dollars, from $2 per 1,000 requests, with no subscription and no monthly minimum. Over the last 30 days, 99.2% of Perplexity calls through AnyAPI succeeded, with a median response time of 42.1 seconds across 387 measured calls.

Pricing is in US dollars, from $2 per 1,000 requests, with no subscription and no monthly minimum. You fund one USD wallet, each call draws it down, and a failed request costs $0.

One endpoint: search. Every one takes the same authentication and returns the same normalized response shape, so reaching a second Perplexity endpoint is a change of URL and nothing else.

Over the last 30 days, 99.2% of Perplexity calls through AnyAPI succeeded, with a median response time of 42.1 seconds across 387 measured calls. These are AnyAPI's own measurements of traffic through the gateway, recomputed continuously, not a published service-level target.