Perplexity API free tier: limits and models

What Perplexity API's free tier allows

Usage tiers are set by cumulative API credit purchases and never downgrade. Tier 0 ($0 purchased) allows 1 query/second and 50 requests/minute on the Agent API; Tier 1 ($50+) allows 3 QPS and 150/min, rising to 33 QPS and 2,000/min at Tier 4. The Search API is separately limited to 50 requests/second at every tier. Tier 0 sets a rate ceiling but is not a free token grant, so credits are still required to make calls.

Published limits: 50 requests per minute
Free access type: Metered access
Credit card: Not required
Protocol: OpenAI-compatible at https://api.perplexity.ai
Lifecycle: Active
Sources reviewed: 2026-07-25

Perplexity Pro subscribers receive a monthly API credit allowance through their subscription; that allowance is not documented on the rate-limits page.

Where Perplexity API sits in this catalog

Perplexity API is one of 6 metered access entries among the 25 providers detailed here. It asks for no credit card, which is true of 23 of the 25. It publishes fixed numbers — 50 requests per minute — which only 9 of the 25 do.

Compared with	Published limits	Card	Endpoint
Perplexity API (this page)	50 requests per minute	Not required	`api.perplexity.ai`
DeepInfra	Enforced but not published	Not required	`api.deepinfra.com`
Chutes	Published per paid plan	Not required	`llm.chutes.ai`
Scaleway Generative APIs	Enforced but not published	Required	`api.scaleway.ai`

Models Perplexity API lists as free

sonar — not part of any family this catalog tracks across providers
sonar-pro — not part of any family this catalog tracks across providers
sonar-reasoning — not part of any family this catalog tracks across providers

The models above do not fall into any of the multi-provider families this catalog tracks, so Perplexity API is the only route to them here.

Checking a Perplexity API key

The endpoint answers the CORS preflight with 404 and no allow-origin header, so a browser refuses to send the Authorization header. That was measured against https://api.perplexity.ai on 2026-07-25.

So the browser checker cannot reach it and does not pretend otherwise. Run this instead:

#!/usr/bin/env sh
set -eu

: "${PERPLEXITY_API_KEY:?Set PERPLEXITY_API_KEY to a key you created yourself at the provider console}"

# Prints the models this key can reach, then the HTTP status on its own line so
# 200, 401, and 429 stay distinguishable.
curl --silent --show-error \
  --write-out '\nHTTP %{http_code}\n' \
  --header "Authorization: Bearer $PERPLEXITY_API_KEY" \
  'https://api.perplexity.ai/models'

Using a Perplexity API key

Perplexity API serves the OpenAI chat completions protocol at https://api.perplexity.ai. Point any client that accepts a custom base URL at it, and let the client read the key from PERPLEXITY_API_KEY so the value never lands in a config file:

# Merge this snippet into ~/.codex/config.toml.
# Project-level config cannot select a custom model provider.
model = "sonar"
model_provider = "perplexity"

[model_providers.perplexity]
name = "Perplexity API OpenAI-compatible gateway"
base_url = "https://api.perplexity.ai"
env_key = "PERPLEXITY_API_KEY"
wire_api = "responses"

Questions about the Perplexity API free tier

Does Perplexity API ask for a credit card?

No. Perplexity API is one of 23 providers here that hand out free access without a card, so the only cost of trying it is the signup.

What are Perplexity API's free-tier rate limits?

Perplexity API publishes 50 requests per minute. Those are the numbers in its own documentation as reviewed on 2026-07-25.

What happens when a Perplexity API key hits the limit?

The endpoint answers 429. That is a statement about the request that was refused, not about how much quota is left; only a reset header from the provider tells you when it clears.

Is the Perplexity API free tier going away?

Nothing in Perplexity API's own documentation says so as of 2026-07-25. Perplexity Pro subscribers receive a monthly API credit allowance through their subscription; that allowance is not documented on the rate-limits page.

Can Perplexity API be used with Codex, Cline, or Continue?

Yes. Perplexity API serves the OpenAI chat completions protocol at https://api.perplexity.ai, so any client that accepts a custom base URL can use it. Claude Code is the exception, because it speaks the Anthropic protocol instead.

Official sources

Perplexity rate limits and usage tiershttps://docs.perplexity.ai/docs/admin/rate-limits-usage-tiers
Perplexity pricinghttps://docs.perplexity.ai/docs/getting-started/pricing
Perplexity OpenAI compatibilityhttps://docs.perplexity.ai/docs/agent-api/openai-compatibility

Every figure above was read from those pages on 2026-07-25. Where a provider states a limit only inside a console, this catalog records that fact instead of a number. See the methodology for how an entry gets in and how it gets corrected.