How Much Does the Perplexity API Cost?
Perplexity's API gives agents grounded search answers. The cost is per-request with model-dependent pricing — and search-happy agents generate requests.
How Perplexity pricing works
Per-request pricing tied to the model used, with web-search queries billed per call.
Usage scales directly with how often agents ask.
The hidden cost
Retry loops re-ask the same question — each one billed.
Agents that search excessively in loops multiply requests.
What it really costs
Per-request rate × request volume. Velocity limits and per-agent caps control the volume.
Where the money goes
| Cost bucket | How to control it |
|---|---|
| Per-request rates | Model selection |
| Retry loops | Velocity limit |
| Excessive search | Per-agent daily ceiling |
FAQ
Is Perplexity API priced per token or per request?
Per-request for search queries, with model-based pricing. Check current docs for exact rates.
Can I cap a research agent's search spend?
Yes — per-agent ceilings and category rules.
Related
Stop the next $12,400 night.
One API call (or MCP tool) in front of every agent transaction — APPROVED, BLOCKED, or FLAGGED, deterministic, ~5 ms, fully logged.
See plans — from $99/mo Try a live check