Perplexity · Rate Limits

Perplexity Rate Limits

Perplexity Rate Limits is the rate-limit profile for Perplexity on the APIs.io network — every limit transcribed verbatim from the provider’s own documentation on 2026-11-04.

It captures 26 rate-limit definitions, including Agent API request limit Tier 0 — 1 QPS; Agent API request limit Tier 1 — 3 QPS; Agent API request limit Tier 2 — 8 QPS.

Tagged areas include Artificial Intelligence, LLM, Search, Agents, and Embeddings.

26 Limits
Transcribed from the provider's documentation on 2026-11-04 — docs.perplexity.ai/docs/admin/rate-limits-usage-tiers.md.
View Source
Artificial IntelligenceLLMSearchAgentsEmbeddingsResearchAgentic CommerceFoundation Models

Limits

Agent API request limit Tier 0 per-organizationTier 0
1 QPS
POST /v1/agent
· per 1 second
Agent API request limit Tier 1 per-organizationTier 1
3 QPS
POST /v1/agent
· per 1 second
Agent API request limit Tier 2 per-organizationTier 2
8 QPS
POST /v1/agent
· per 1 second
Agent API request limit Tier 3 per-organizationTier 3
17 QPS
POST /v1/agent
· per 1 second
Agent API request limit Tier 4 per-organizationTier 4
33 QPS
POST /v1/agent
· per 1 second
Agent API request limit Tier 5 per-organizationTier 5
33 QPS
POST /v1/agent
· per 1 second
Agent API TPM Tier 0 per-organization-per-modelTier 0
5000000
· per 1 minute
Agent API TPH Tier 0 per-organization-per-modelTier 0
300000000
· per 1 hour
Agent API TPM Tier 1 per-organization-per-modelTier 1
6000000
· per 1 minute
Agent API TPH Tier 1 per-organization-per-modelTier 1
360000000
· per 1 hour
Agent API TPM Tier 2 per-organization-per-modelTier 2
8000000
· per 1 minute
Agent API TPH Tier 2 per-organization-per-modelTier 2
480000000
· per 1 hour
Agent API TPM Tier 3 per-organization-per-modelTier 3
10000000
· per 1 minute
Agent API TPH Tier 3 per-organization-per-modelTier 3
600000000
· per 1 hour
Agent API TPM Tier 4 per-organization-per-modelTier 4
13000000
· per 1 minute
Agent API TPH Tier 4 per-organization-per-modelTier 4
780000000
· per 1 hour
Agent API TPM Tier 5 per-organization-per-modelTier 5
16000000
· per 1 minute
Agent API TPH Tier 5 per-organization-per-modelTier 5
960000000
· per 1 hour
Search API per-organization
50 query units per second
POST /search
· per 1 second
Search API burst per-organizationburst
50 query units
POST /search
Embeddings API Tier 0 per-organizationTier 0
85 QPS
· per 1 second
Embeddings API Tiers 1–3 per-organizationTiers 1–3
170 QPS
· per 1 second
Embeddings API Tiers 4–5 per-organizationTiers 4–5
335 QPS
· per 1 second
Contextualized Embeddings Tier 0 per-organizationTier 0
415 chunks/s
· per 1 second
Contextualized Embeddings Tiers 1–3 per-organizationTiers 1–3
835 chunks/s
· per 1 second
Contextualized Embeddings Tiers 4–5 per-organizationTiers 4–5
1,670 chunks/s
· per 1 second

Work with this as data

Every rate limit here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for rate limits

4 MCP tools reach this
  • find_rate_limitsBrowse and filter every rate limit in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This rate limit 
curl "https://apis.io/api/v1/rate-limits/perplexity-rate-limits"
All rate limits 
curl "https://apis.io/api/v1/rate-limits?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.